SAVRN
Search Contact SAVRN

Open-weight model

visualrl-rscore

by Zeyuan Yang Miiche/visualrl-rscore

Parameters
Context
Weights2.0 GB
License
AccessOpen weights
Monthly Downloads

Model Card

The publisher has not written a card for this model.

Identity and Version

Repository
Miiche/visualrl-rscore
Publisher
Zeyuan Yang
Task
Not stated by the source
Modality
Other
Library
Not stated by the source
Parameters
Not stated by the source
Languages
Not stated by the source
Revision
f46f51c9a1e20ab3158748fb069b43e812d9525f
First published
2026-08-27
Last updated
2026-09-18

Files and Weights

4,975 files, 2.0 GB in total.

Configuration1086 files · 753.9 KB
Other1914 files · 988.5 MB
Every file (first 3,000)
FileTypeSizeSHA-256
baseeval/blink.claude_opus_4_8.q3vl2b.jsonConfiguration287 B
baseeval/chartqa.claude_opus_4_8.q3vl2b.jsonConfiguration289 B
baseeval/hallusionbench.claude_opus_4_8.q3vl2b.jsonConfiguration286 B
baseeval/logicvista.claude_opus_4_8.q3vl2b.jsonConfiguration289 B
baseeval/mathverse.claude_opus_4_8.q3vl2b.jsonConfiguration286 B
baseeval/mathvision.claude_opus_4_8.q3vl2b.jsonConfiguration286 B
baseeval/mathvista.claude_opus_4_8.q3vl2b.jsonConfiguration288 B
baseeval/mmbench.claude_opus_4_8.q3vl2b.jsonConfiguration287 B
baseeval/mme.claude_opus_4_8.q3vl2b.jsonConfiguration289 B
baseeval/mmmu.claude_opus_4_8.q3vl2b.jsonConfiguration286 B
baseeval/mmmu_pro.claude_opus_4_8.q3vl2b.jsonConfiguration289 B
baseeval/mmstar.claude_opus_4_8.q3vl2b.jsonConfiguration287 B
baseeval/mmvet.claude_opus_4_8.q3vl2b.jsonConfiguration289 B
baseeval/perceptionbench.claude_opus_4_8.q3vl2b.jsonConfiguration288 B
baseeval/realworldqa.claude_opus_4_8.q3vl2b.jsonConfiguration285 B
baseeval/scienceqa.claude_opus_4_8.q3vl2b.jsonConfiguration287 B
baseeval/visnumbench.claude_opus_4_8.q3vl2b.jsonConfiguration288 B
cond_scores/blink.claude_opus_4_8.gemma3_27b.jsonConfiguration382 B
cond_scores/blink.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration396 B
cond_scores/blink.claude_opus_4_8.llama4s17b.jsonConfiguration387 B
cond_scores/blink.claude_opus_4_8.llama4s17b_mc.jsonConfiguration411 B
cond_scores/blink.claude_opus_4_8.q35_9b.jsonConfiguration354 B
cond_scores/blink.claude_opus_4_8.q35_9b_mc.jsonConfiguration353 B
cond_scores/blink.claude_opus_4_8.q3vl2b.jsonConfiguration349 B
cond_scores/blink.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration377 B
cond_scores/blink.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration378 B
cond_scores/blink.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration377 B
cond_scores/blink.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration378 B
cond_scores/blink.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration363 B
cond_scores/blink.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration376 B
cond_scores/blink.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration378 B
cond_scores/blink.claude_opus_4_8.q3vl2b_mc.jsonConfiguration364 B
cond_scores/blink.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration377 B
cond_scores/blink.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration377 B
cond_scores/blink.claude_opus_4_8.q3vl4b.jsonConfiguration365 B
cond_scores/blink.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration377 B
cond_scores/blink.claude_opus_4_8.q3vl4b_mc.jsonConfiguration363 B
cond_scores/blink.gpt_5_6_luna.gemma3_27b.jsonConfiguration397 B
cond_scores/blink.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration397 B
cond_scores/blink.gpt_5_6_luna.llama4s17b.jsonConfiguration412 B
cond_scores/blink.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration412 B
cond_scores/blink.gpt_5_6_luna.q35_9b.jsonConfiguration300 B
cond_scores/blink.gpt_5_6_luna.q35_9b_mc.jsonConfiguration300 B
cond_scores/blink.gpt_5_6_luna.q3vl2b.jsonConfiguration309 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration326 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration324 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration325 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration323 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration322 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration323 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration311 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration325 B
cond_scores/blink.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration326 B
cond_scores/blink.gpt_5_6_luna.q3vl4b.jsonConfiguration301 B
cond_scores/blink.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration323 B
cond_scores/blink.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration310 B
cond_scores/chartqa.claude_opus_4_8.gemma3_27b.jsonConfiguration397 B
cond_scores/chartqa.claude_opus_4_8.llama4s17b.jsonConfiguration365 B
cond_scores/chartqa.claude_opus_4_8.q35_9b.jsonConfiguration299 B
cond_scores/chartqa.claude_opus_4_8.q3vl2b.jsonConfiguration294 B
cond_scores/chartqa.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/chartqa.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/chartqa.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration323 B
cond_scores/chartqa.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration324 B
cond_scores/chartqa.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration306 B
cond_scores/chartqa.claude_opus_4_8.q3vl4b.jsonConfiguration312 B
cond_scores/chartqa.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration320 B
cond_scores/chartqa.gpt_5_6_luna.gemma3_27b.jsonConfiguration394 B
cond_scores/chartqa.gpt_5_6_luna.llama4s17b.jsonConfiguration413 B
cond_scores/chartqa.gpt_5_6_luna.q35_9b.jsonConfiguration301 B
cond_scores/chartqa.gpt_5_6_luna.q3vl2b.jsonConfiguration294 B
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration323 B
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration323 B
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration320 B
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration308 B
cond_scores/chartqa.gpt_5_6_luna.q3vl4b.jsonConfiguration310 B
cond_scores/chartqa.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration320 B
cond_scores/hallusionbench.claude_opus_4_8.gemma3_27b.jsonConfiguration394 B
cond_scores/hallusionbench.claude_opus_4_8.llama4s17b.jsonConfiguration414 B
cond_scores/hallusionbench.claude_opus_4_8.q35_9b.jsonConfiguration301 B
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b.jsonConfiguration311 B
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration321 B
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration322 B
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration324 B
cond_scores/hallusionbench.claude_opus_4_8.q3vl4b.jsonConfiguration309 B
cond_scores/hallusionbench.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration323 B
cond_scores/hallusionbench.gpt_5_6_luna.gemma3_27b.jsonConfiguration396 B
cond_scores/hallusionbench.gpt_5_6_luna.llama4s17b.jsonConfiguration412 B
cond_scores/hallusionbench.gpt_5_6_luna.q35_9b.jsonConfiguration303 B
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b.jsonConfiguration310 B
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration322 B
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration321 B
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration324 B
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration323 B
cond_scores/hallusionbench.gpt_5_6_luna.q3vl4b.jsonConfiguration298 B
cond_scores/hallusionbench.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration325 B
cond_scores/logicvista.claude_opus_4_8.gemma3_27b.jsonConfiguration395 B
cond_scores/logicvista.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration395 B
cond_scores/logicvista.claude_opus_4_8.llama4s17b.jsonConfiguration414 B
cond_scores/logicvista.claude_opus_4_8.llama4s17b_mc.jsonConfiguration412 B
cond_scores/logicvista.claude_opus_4_8.q35_9b.jsonConfiguration300 B
cond_scores/logicvista.claude_opus_4_8.q35_9b_mc.jsonConfiguration300 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b.jsonConfiguration311 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration307 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration321 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration308 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration324 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration324 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration308 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration324 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_mc.jsonConfiguration310 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration324 B
cond_scores/logicvista.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration324 B
cond_scores/logicvista.claude_opus_4_8.q3vl4b.jsonConfiguration309 B
cond_scores/logicvista.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration325 B
cond_scores/logicvista.claude_opus_4_8.q3vl4b_mc.jsonConfiguration311 B
cond_scores/logicvista.gpt_5_6_luna.gemma3_27b.jsonConfiguration366 B
cond_scores/logicvista.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration395 B
cond_scores/logicvista.gpt_5_6_luna.llama4s17b.jsonConfiguration414 B
cond_scores/logicvista.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration411 B
cond_scores/logicvista.gpt_5_6_luna.q35_9b.jsonConfiguration300 B
cond_scores/logicvista.gpt_5_6_luna.q35_9b_mc.jsonConfiguration301 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b.jsonConfiguration310 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration324 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration324 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration312 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration325 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration322 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration324 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration324 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration311 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration324 B
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration307 B
cond_scores/logicvista.gpt_5_6_luna.q3vl4b.jsonConfiguration310 B
cond_scores/logicvista.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration324 B
cond_scores/logicvista.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration310 B
cond_scores/mathverse.claude_opus_4_8.gemma3_27b.jsonConfiguration398 B
cond_scores/mathverse.claude_opus_4_8.llama4s17b.jsonConfiguration412 B
cond_scores/mathverse.claude_opus_4_8.q35_9b.jsonConfiguration299 B
cond_scores/mathverse.claude_opus_4_8.q3vl2b.jsonConfiguration295 B
cond_scores/mathverse.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration326 B
cond_scores/mathverse.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration323 B
cond_scores/mathverse.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration326 B
cond_scores/mathverse.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration322 B
cond_scores/mathverse.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration321 B
cond_scores/mathverse.claude_opus_4_8.q3vl4b.jsonConfiguration311 B
cond_scores/mathverse.gpt_5_6_luna.gemma3_27b.jsonConfiguration397 B
cond_scores/mathverse.gpt_5_6_luna.llama4s17b.jsonConfiguration413 B
cond_scores/mathverse.gpt_5_6_luna.q35_9b.jsonConfiguration298 B
cond_scores/mathverse.gpt_5_6_luna.q3vl2b.jsonConfiguration300 B
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration324 B
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration325 B
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration323 B
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration323 B
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration323 B
cond_scores/mathverse.gpt_5_6_luna.q3vl4b.jsonConfiguration313 B
cond_scores/mathvision.claude_opus_4_8.gemma3_27b.jsonConfiguration367 B
cond_scores/mathvision.claude_opus_4_8.llama4s17b.jsonConfiguration413 B
cond_scores/mathvision.claude_opus_4_8.q35_9b.jsonConfiguration301 B
cond_scores/mathvision.claude_opus_4_8.q3vl2b.jsonConfiguration311 B
cond_scores/mathvision.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration324 B
cond_scores/mathvision.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/mathvision.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration322 B
cond_scores/mathvision.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration323 B
cond_scores/mathvision.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration324 B
cond_scores/mathvision.claude_opus_4_8.q3vl4b.jsonConfiguration311 B
cond_scores/mathvision.gpt_5_6_luna.gemma3_27b.jsonConfiguration363 B
cond_scores/mathvision.gpt_5_6_luna.llama4s17b.jsonConfiguration415 B
cond_scores/mathvision.gpt_5_6_luna.q35_9b.jsonConfiguration300 B
cond_scores/mathvision.gpt_5_6_luna.q3vl2b.jsonConfiguration309 B
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration322 B
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration324 B
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration324 B
cond_scores/mathvision.gpt_5_6_luna.q3vl4b.jsonConfiguration309 B
cond_scores/mathvista.claude_opus_4_8.gemma3_27b.jsonConfiguration395 B
cond_scores/mathvista.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration396 B
cond_scores/mathvista.claude_opus_4_8.llama4s17b.jsonConfiguration415 B
cond_scores/mathvista.claude_opus_4_8.llama4s17b_mc.jsonConfiguration414 B
cond_scores/mathvista.claude_opus_4_8.q35_9b.jsonConfiguration356 B
cond_scores/mathvista.claude_opus_4_8.q35_9b_mc.jsonConfiguration357 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b.jsonConfiguration368 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration379 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration377 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration377 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration376 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration377 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration379 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration377 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_mc.jsonConfiguration366 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration380 B
cond_scores/mathvista.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration378 B
cond_scores/mathvista.claude_opus_4_8.q3vl4b.jsonConfiguration364 B
cond_scores/mathvista.claude_opus_4_8.q3vl4b_mc.jsonConfiguration365 B
cond_scores/mathvista.gpt_5_6_luna.gemma3_27b.jsonConfiguration397 B
cond_scores/mathvista.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration398 B
cond_scores/mathvista.gpt_5_6_luna.llama4s17b.jsonConfiguration415 B
cond_scores/mathvista.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration414 B
cond_scores/mathvista.gpt_5_6_luna.q35_9b.jsonConfiguration300 B
cond_scores/mathvista.gpt_5_6_luna.q35_9b_mc.jsonConfiguration286 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b.jsonConfiguration312 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration325 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration324 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration322 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration321 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration321 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration323 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration321 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration310 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration325 B
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration322 B
cond_scores/mathvista.gpt_5_6_luna.q3vl4b.jsonConfiguration310 B
cond_scores/mathvista.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration311 B
cond_scores/mmbench.claude_opus_4_8.gemma3_27b.jsonConfiguration397 B
cond_scores/mmbench.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration368 B
cond_scores/mmbench.claude_opus_4_8.llama4s17b.jsonConfiguration412 B
cond_scores/mmbench.claude_opus_4_8.llama4s17b_mc.jsonConfiguration369 B
cond_scores/mmbench.claude_opus_4_8.q35_9b.jsonConfiguration300 B
cond_scores/mmbench.claude_opus_4_8.q35_9b_mc.jsonConfiguration288 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b.jsonConfiguration310 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration324 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration323 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration321 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration321 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration322 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration325 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_mc.jsonConfiguration311 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration322 B
cond_scores/mmbench.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration323 B
cond_scores/mmbench.claude_opus_4_8.q3vl4b.jsonConfiguration308 B
cond_scores/mmbench.claude_opus_4_8.q3vl4b_mc.jsonConfiguration311 B
cond_scores/mmbench.gpt_5_6_luna.gemma3_27b.jsonConfiguration396 B
cond_scores/mmbench.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration396 B
cond_scores/mmbench.gpt_5_6_luna.llama4s17b.jsonConfiguration413 B
cond_scores/mmbench.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration369 B
cond_scores/mmbench.gpt_5_6_luna.q35_9b.jsonConfiguration300 B
cond_scores/mmbench.gpt_5_6_luna.q35_9b_mc.jsonConfiguration289 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b.jsonConfiguration312 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration321 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration326 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration323 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration308 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration320 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration324 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration325 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration311 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration322 B
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration320 B
cond_scores/mmbench.gpt_5_6_luna.q3vl4b.jsonConfiguration308 B
cond_scores/mmbench.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration309 B
cond_scores/mme.claude_opus_4_8.gemma3_27b.jsonConfiguration396 B
cond_scores/mme.claude_opus_4_8.llama4s17b.jsonConfiguration411 B
cond_scores/mme.claude_opus_4_8.q35_9b.jsonConfiguration354 B
cond_scores/mme.claude_opus_4_8.q3vl2b.jsonConfiguration364 B
cond_scores/mme.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration362 B
cond_scores/mme.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration377 B
cond_scores/mme.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration377 B
cond_scores/mme.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration377 B
cond_scores/mme.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration362 B
cond_scores/mme.claude_opus_4_8.q3vl4b.jsonConfiguration351 B
cond_scores/mme.gpt_5_6_luna.gemma3_27b.jsonConfiguration396 B
cond_scores/mme.gpt_5_6_luna.llama4s17b.jsonConfiguration412 B
cond_scores/mme.gpt_5_6_luna.q35_9b.jsonConfiguration298 B
cond_scores/mme.gpt_5_6_luna.q3vl2b.jsonConfiguration310 B
cond_scores/mme.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration306 B
cond_scores/mme.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration322 B
cond_scores/mme.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration324 B
cond_scores/mme.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration324 B
cond_scores/mme.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration322 B
cond_scores/mme.gpt_5_6_luna.q3vl4b.jsonConfiguration308 B
cond_scores/mmmu.claude_opus_4_8.gemma3_27b.jsonConfiguration396 B
cond_scores/mmmu.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration396 B
cond_scores/mmmu.claude_opus_4_8.llama4s17b.jsonConfiguration414 B
cond_scores/mmmu.claude_opus_4_8.llama4s17b_mc.jsonConfiguration414 B
cond_scores/mmmu.claude_opus_4_8.q35_9b.jsonConfiguration356 B
cond_scores/mmmu.claude_opus_4_8.q35_9b_mc.jsonConfiguration351 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b.jsonConfiguration367 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration364 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration379 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration376 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration377 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration378 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration379 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration379 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_mc.jsonConfiguration366 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration379 B
cond_scores/mmmu.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration363 B
cond_scores/mmmu.claude_opus_4_8.q3vl4b.jsonConfiguration365 B
cond_scores/mmmu.claude_opus_4_8.q3vl4b_mc.jsonConfiguration365 B
cond_scores/mmmu.gpt_5_6_luna.gemma3_27b.jsonConfiguration397 B
cond_scores/mmmu.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration395 B
cond_scores/mmmu.gpt_5_6_luna.llama4s17b.jsonConfiguration411 B
cond_scores/mmmu.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration413 B
cond_scores/mmmu.gpt_5_6_luna.q35_9b.jsonConfiguration302 B
cond_scores/mmmu.gpt_5_6_luna.q35_9b_mc.jsonConfiguration300 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b.jsonConfiguration310 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration308 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration326 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration324 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration324 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration325 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration324 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration310 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration309 B
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration308 B
cond_scores/mmmu.gpt_5_6_luna.q3vl4b.jsonConfiguration310 B
cond_scores/mmmu.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration310 B
cond_scores/mmmu_pro.claude_opus_4_8.gemma3_27b.jsonConfiguration396 B
cond_scores/mmmu_pro.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration397 B
cond_scores/mmmu_pro.claude_opus_4_8.llama4s17b.jsonConfiguration414 B
cond_scores/mmmu_pro.claude_opus_4_8.llama4s17b_mc.jsonConfiguration415 B
cond_scores/mmmu_pro.claude_opus_4_8.q35_9b.jsonConfiguration353 B
cond_scores/mmmu_pro.claude_opus_4_8.q35_9b_mc.jsonConfiguration353 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b.jsonConfiguration363 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration381 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration378 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration377 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration382 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration367 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration377 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration363 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_mc.jsonConfiguration365 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration378 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration377 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl4b.jsonConfiguration364 B
cond_scores/mmmu_pro.claude_opus_4_8.q3vl4b_mc.jsonConfiguration365 B
cond_scores/mmmu_pro.gpt_5_6_luna.gemma3_27b.jsonConfiguration397 B
cond_scores/mmmu_pro.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration398 B
cond_scores/mmmu_pro.gpt_5_6_luna.llama4s17b.jsonConfiguration413 B
cond_scores/mmmu_pro.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration414 B
cond_scores/mmmu_pro.gpt_5_6_luna.q35_9b.jsonConfiguration298 B
cond_scores/mmmu_pro.gpt_5_6_luna.q35_9b_mc.jsonConfiguration299 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b.jsonConfiguration310 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration323 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration323 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration310 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration313 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration323 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration326 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration308 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration324 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration323 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl4b.jsonConfiguration311 B
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration310 B
cond_scores/mmstar.claude_opus_4_8.gemma3_27b.jsonConfiguration397 B
cond_scores/mmstar.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration395 B
cond_scores/mmstar.claude_opus_4_8.llama4s17b.jsonConfiguration412 B
cond_scores/mmstar.claude_opus_4_8.llama4s17b_mc.jsonConfiguration412 B
cond_scores/mmstar.claude_opus_4_8.q35_9b.jsonConfiguration299 B
cond_scores/mmstar.claude_opus_4_8.q35_9b_mc.jsonConfiguration299 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b.jsonConfiguration310 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration321 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration323 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration310 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration323 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration309 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration323 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_mc.jsonConfiguration310 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration322 B
cond_scores/mmstar.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration323 B
cond_scores/mmstar.claude_opus_4_8.q3vl4b.jsonConfiguration296 B
cond_scores/mmstar.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration324 B
cond_scores/mmstar.claude_opus_4_8.q3vl4b_mc.jsonConfiguration295 B
cond_scores/mmstar.gpt_5_6_luna.gemma3_27b.jsonConfiguration395 B
cond_scores/mmstar.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration395 B
cond_scores/mmstar.gpt_5_6_luna.llama4s17b.jsonConfiguration413 B
cond_scores/mmstar.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration414 B
cond_scores/mmstar.gpt_5_6_luna.q35_9b.jsonConfiguration299 B
cond_scores/mmstar.gpt_5_6_luna.q35_9b_mc.jsonConfiguration302 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b.jsonConfiguration308 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration324 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration323 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration321 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration322 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration310 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration323 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration309 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration323 B
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration323 B
cond_scores/mmstar.gpt_5_6_luna.q3vl4b.jsonConfiguration295 B
cond_scores/mmstar.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration321 B
cond_scores/mmstar.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration310 B
cond_scores/mmvet.claude_opus_4_8.gemma3_27b.jsonConfiguration396 B
cond_scores/mmvet.claude_opus_4_8.llama4s17b.jsonConfiguration399 B
cond_scores/mmvet.claude_opus_4_8.q35_9b.jsonConfiguration355 B
cond_scores/mmvet.claude_opus_4_8.q3vl2b.jsonConfiguration350 B
cond_scores/mmvet.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration379 B
cond_scores/mmvet.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration379 B
cond_scores/mmvet.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration377 B
cond_scores/mmvet.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration380 B
cond_scores/mmvet.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration377 B
cond_scores/mmvet.claude_opus_4_8.q3vl4b.jsonConfiguration364 B
cond_scores/mmvet.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration346 B
cond_scores/mmvet.gpt_5_6_luna.gemma3_27b.jsonConfiguration394 B
cond_scores/mmvet.gpt_5_6_luna.llama4s17b.jsonConfiguration414 B
cond_scores/mmvet.gpt_5_6_luna.q35_9b.jsonConfiguration300 B
cond_scores/mmvet.gpt_5_6_luna.q3vl2b.jsonConfiguration295 B
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration324 B
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration322 B
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration324 B
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration323 B
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration325 B
cond_scores/mmvet.gpt_5_6_luna.q3vl4b.jsonConfiguration309 B
cond_scores/mmvet.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration321 B
cond_scores/perceptionbench.claude_opus_4_8.gemma3_27b.jsonConfiguration395 B
cond_scores/perceptionbench.claude_opus_4_8.llama4s17b.jsonConfiguration413 B
cond_scores/perceptionbench.claude_opus_4_8.q35_9b.jsonConfiguration344 B
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b.jsonConfiguration369 B
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration380 B
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration381 B
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration381 B
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration381 B
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration382 B
cond_scores/perceptionbench.claude_opus_4_8.q3vl4b.jsonConfiguration367 B
cond_scores/perceptionbench.gpt_5_6_luna.gemma3_27b.jsonConfiguration397 B
cond_scores/perceptionbench.gpt_5_6_luna.llama4s17b.jsonConfiguration414 B
cond_scores/perceptionbench.gpt_5_6_luna.q35_9b.jsonConfiguration302 B
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b.jsonConfiguration310 B
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration324 B
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration323 B
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration322 B
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration324 B
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration324 B
cond_scores/perceptionbench.gpt_5_6_luna.q3vl4b.jsonConfiguration309 B
cond_scores/realworldqa.claude_opus_4_8.gemma3_27b.jsonConfiguration395 B
cond_scores/realworldqa.claude_opus_4_8.llama4s17b.jsonConfiguration387 B
cond_scores/realworldqa.claude_opus_4_8.q35_9b.jsonConfiguration341 B
cond_scores/realworldqa.claude_opus_4_8.q3vl2b.jsonConfiguration364 B
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration376 B
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration378 B
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration362 B
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration378 B
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration378 B
cond_scores/realworldqa.claude_opus_4_8.q3vl4b.jsonConfiguration363 B
cond_scores/realworldqa.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration378 B
cond_scores/realworldqa.gpt_5_6_luna.gemma3_27b.jsonConfiguration394 B
cond_scores/realworldqa.gpt_5_6_luna.llama4s17b.jsonConfiguration411 B
cond_scores/realworldqa.gpt_5_6_luna.q35_9b.jsonConfiguration302 B
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b.jsonConfiguration311 B
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration322 B
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration323 B
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration324 B
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration323 B
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration325 B
cond_scores/realworldqa.gpt_5_6_luna.q3vl4b.jsonConfiguration310 B
cond_scores/realworldqa.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration322 B
cond_scores/scienceqa.claude_opus_4_8.gemma3_27b.jsonConfiguration393 B
cond_scores/scienceqa.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration397 B
cond_scores/scienceqa.claude_opus_4_8.llama4s17b.jsonConfiguration379 B
cond_scores/scienceqa.claude_opus_4_8.llama4s17b_mc.jsonConfiguration365 B
cond_scores/scienceqa.claude_opus_4_8.q35_9b.jsonConfiguration300 B
cond_scores/scienceqa.claude_opus_4_8.q35_9b_mc.jsonConfiguration300 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b.jsonConfiguration309 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration322 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration323 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration321 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration322 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration323 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration321 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_mc.jsonConfiguration295 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration321 B
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration321 B
cond_scores/scienceqa.claude_opus_4_8.q3vl4b.jsonConfiguration294 B
cond_scores/scienceqa.claude_opus_4_8.q3vl4b_mc.jsonConfiguration292 B
cond_scores/scienceqa.gpt_5_6_luna.gemma3_27b.jsonConfiguration393 B
cond_scores/scienceqa.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration395 B
cond_scores/scienceqa.gpt_5_6_luna.llama4s17b.jsonConfiguration409 B
cond_scores/scienceqa.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration365 B
cond_scores/scienceqa.gpt_5_6_luna.q35_9b.jsonConfiguration301 B
cond_scores/scienceqa.gpt_5_6_luna.q35_9b_mc.jsonConfiguration298 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b.jsonConfiguration296 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration325 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration323 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration319 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration323 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration322 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration310 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration321 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration321 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl4b.jsonConfiguration293 B
cond_scores/scienceqa.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration292 B
cond_scores/visnumbench.claude_opus_4_8.gemma3_27b.jsonConfiguration395 B
cond_scores/visnumbench.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration396 B
cond_scores/visnumbench.claude_opus_4_8.llama4s17b.jsonConfiguration413 B
cond_scores/visnumbench.claude_opus_4_8.llama4s17b_mc.jsonConfiguration414 B
cond_scores/visnumbench.claude_opus_4_8.q35_9b.jsonConfiguration302 B
cond_scores/visnumbench.claude_opus_4_8.q35_9b_mc.jsonConfiguration300 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b.jsonConfiguration311 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration324 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration324 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration325 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration324 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration322 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration323 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_mc.jsonConfiguration298 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration323 B
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration324 B
cond_scores/visnumbench.claude_opus_4_8.q3vl4b.jsonConfiguration309 B
cond_scores/visnumbench.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration325 B
cond_scores/visnumbench.claude_opus_4_8.q3vl4b_mc.jsonConfiguration311 B
cond_scores/visnumbench.gpt_5_6_luna.gemma3_27b.jsonConfiguration396 B
cond_scores/visnumbench.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration395 B
cond_scores/visnumbench.gpt_5_6_luna.llama4s17b.jsonConfiguration415 B
cond_scores/visnumbench.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration415 B
cond_scores/visnumbench.gpt_5_6_luna.q35_9b.jsonConfiguration300 B
cond_scores/visnumbench.gpt_5_6_luna.q35_9b_mc.jsonConfiguration301 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b.jsonConfiguration309 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration323 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration324 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration325 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration324 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration324 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration324 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration324 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration297 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration325 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration324 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl4b.jsonConfiguration309 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration324 B
cond_scores/visnumbench.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration309 B
pr_split/blink.claude_opus_4_8.gemma3_27b.jsonConfiguration332 B
pr_split/blink.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration332 B
pr_split/blink.claude_opus_4_8.llama4s17b.jsonConfiguration333 B
pr_split/blink.claude_opus_4_8.llama4s17b_mc.jsonConfiguration348 B
pr_split/blink.claude_opus_4_8.q35_9b.jsonConfiguration562 B
pr_split/blink.claude_opus_4_8.q35_9b_mc.jsonConfiguration561 B
pr_split/blink.claude_opus_4_8.q3vl2b.jsonConfiguration570 B
pr_split/blink.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration585 B
pr_split/blink.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration599 B
pr_split/blink.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration601 B
pr_split/blink.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration585 B
pr_split/blink.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration570 B
pr_split/blink.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration599 B
pr_split/blink.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration600 B
pr_split/blink.claude_opus_4_8.q3vl2b_mc.jsonConfiguration586 B
pr_split/blink.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration584 B
pr_split/blink.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration598 B
pr_split/blink.claude_opus_4_8.q3vl4b.jsonConfiguration586 B
pr_split/blink.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration600 B
pr_split/blink.claude_opus_4_8.q3vl4b_mc.jsonConfiguration583 B
pr_split/blink.gpt_5_6_luna.gemma3_27b.jsonConfiguration328 B
pr_split/blink.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration328 B
pr_split/blink.gpt_5_6_luna.llama4s17b.jsonConfiguration329 B
pr_split/blink.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration343 B
pr_split/blink.gpt_5_6_luna.q35_9b.jsonConfiguration572 B
pr_split/blink.gpt_5_6_luna.q35_9b_mc.jsonConfiguration572 B
pr_split/blink.gpt_5_6_luna.q3vl2b.jsonConfiguration583 B
pr_split/blink.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration597 B
pr_split/blink.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration580 B
pr_split/blink.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration595 B
pr_split/blink.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration597 B
pr_split/blink.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration596 B
pr_split/blink.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration582 B
pr_split/blink.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration596 B
pr_split/blink.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration567 B
pr_split/blink.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration597 B
pr_split/blink.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration596 B
pr_split/blink.gpt_5_6_luna.q3vl4b.jsonConfiguration540 B
pr_split/blink.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration580 B
pr_split/blink.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration581 B
pr_split/chartqa.claude_opus_4_8.gemma3_27b.jsonConfiguration334 B
pr_split/chartqa.claude_opus_4_8.llama4s17b.jsonConfiguration346 B
pr_split/chartqa.claude_opus_4_8.q35_9b.jsonConfiguration574 B
pr_split/chartqa.claude_opus_4_8.q3vl2b.jsonConfiguration529 B
pr_split/chartqa.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration600 B
pr_split/chartqa.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration589 B
pr_split/chartqa.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration600 B
pr_split/chartqa.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration598 B
pr_split/chartqa.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration541 B
pr_split/chartqa.claude_opus_4_8.q3vl4b.jsonConfiguration573 B
pr_split/chartqa.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration601 B
pr_split/chartqa.gpt_5_6_luna.gemma3_27b.jsonConfiguration327 B
pr_split/chartqa.gpt_5_6_luna.llama4s17b.jsonConfiguration342 B
pr_split/chartqa.gpt_5_6_luna.q35_9b.jsonConfiguration573 B
pr_split/chartqa.gpt_5_6_luna.q3vl2b.jsonConfiguration525 B
pr_split/chartqa.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration595 B
pr_split/chartqa.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration597 B
pr_split/chartqa.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration596 B
pr_split/chartqa.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration580 B
pr_split/chartqa.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration524 B
pr_split/chartqa.gpt_5_6_luna.q3vl4b.jsonConfiguration568 B
pr_split/chartqa.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration596 B
pr_split/hallusionbench.claude_opus_4_8.gemma3_27b.jsonConfiguration340 B
pr_split/hallusionbench.claude_opus_4_8.llama4s17b.jsonConfiguration356 B
pr_split/hallusionbench.claude_opus_4_8.q35_9b.jsonConfiguration584 B
pr_split/hallusionbench.claude_opus_4_8.q3vl2b.jsonConfiguration594 B
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration577 B
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration609 B
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration608 B
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration592 B
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration607 B
pr_split/hallusionbench.claude_opus_4_8.q3vl4b.jsonConfiguration593 B
pr_split/hallusionbench.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration605 B
pr_split/hallusionbench.gpt_5_6_luna.gemma3_27b.jsonConfiguration334 B
pr_split/hallusionbench.gpt_5_6_luna.llama4s17b.jsonConfiguration351 B
pr_split/hallusionbench.gpt_5_6_luna.q35_9b.jsonConfiguration567 B
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b.jsonConfiguration590 B
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration589 B
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration587 B
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration603 B
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration605 B
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration604 B
pr_split/hallusionbench.gpt_5_6_luna.q3vl4b.jsonConfiguration577 B
pr_split/hallusionbench.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration569 B
pr_split/logicvista.claude_opus_4_8.gemma3_27b.jsonConfiguration337 B
pr_split/logicvista.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration335 B
pr_split/logicvista.claude_opus_4_8.llama4s17b.jsonConfiguration354 B
pr_split/logicvista.claude_opus_4_8.llama4s17b_mc.jsonConfiguration352 B
pr_split/logicvista.claude_opus_4_8.q35_9b.jsonConfiguration578 B
pr_split/logicvista.claude_opus_4_8.q35_9b_mc.jsonConfiguration580 B
pr_split/logicvista.claude_opus_4_8.q3vl2b.jsonConfiguration591 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration587 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration606 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration565 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration604 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration594 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration590 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration604 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_mc.jsonConfiguration592 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration604 B
pr_split/logicvista.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration605 B
pr_split/logicvista.claude_opus_4_8.q3vl4b.jsonConfiguration593 B
pr_split/logicvista.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration602 B
pr_split/logicvista.claude_opus_4_8.q3vl4b_mc.jsonConfiguration577 B
pr_split/logicvista.gpt_5_6_luna.gemma3_27b.jsonConfiguration333 B
pr_split/logicvista.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration333 B
pr_split/logicvista.gpt_5_6_luna.llama4s17b.jsonConfiguration351 B
pr_split/logicvista.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration350 B
pr_split/logicvista.gpt_5_6_luna.q35_9b.jsonConfiguration578 B
pr_split/logicvista.gpt_5_6_luna.q35_9b_mc.jsonConfiguration559 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b.jsonConfiguration576 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration588 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration601 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration588 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration601 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration601 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration602 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration602 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration572 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration604 B
pr_split/logicvista.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration586 B
pr_split/logicvista.gpt_5_6_luna.q3vl4b.jsonConfiguration589 B
pr_split/logicvista.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration599 B
pr_split/logicvista.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration587 B
pr_split/mathverse.claude_opus_4_8.gemma3_27b.jsonConfiguration336 B
pr_split/mathverse.claude_opus_4_8.llama4s17b.jsonConfiguration351 B
pr_split/mathverse.claude_opus_4_8.q35_9b.jsonConfiguration550 B
pr_split/mathverse.claude_opus_4_8.q3vl2b.jsonConfiguration548 B
pr_split/mathverse.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration606 B
pr_split/mathverse.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration605 B
pr_split/mathverse.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration590 B
pr_split/mathverse.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration606 B
pr_split/mathverse.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration604 B
pr_split/mathverse.claude_opus_4_8.q3vl4b.jsonConfiguration579 B
pr_split/mathverse.gpt_5_6_luna.gemma3_27b.jsonConfiguration332 B
pr_split/mathverse.gpt_5_6_luna.llama4s17b.jsonConfiguration349 B
pr_split/mathverse.gpt_5_6_luna.q35_9b.jsonConfiguration577 B
pr_split/mathverse.gpt_5_6_luna.q3vl2b.jsonConfiguration546 B
pr_split/mathverse.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration601 B
pr_split/mathverse.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration603 B
pr_split/mathverse.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration603 B
pr_split/mathverse.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration602 B
pr_split/mathverse.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration600 B
pr_split/mathverse.gpt_5_6_luna.q3vl4b.jsonConfiguration588 B
pr_split/mathvision.claude_opus_4_8.gemma3_27b.jsonConfiguration328 B
pr_split/mathvision.claude_opus_4_8.llama4s17b.jsonConfiguration339 B
pr_split/mathvision.claude_opus_4_8.q35_9b.jsonConfiguration581 B
pr_split/mathvision.claude_opus_4_8.q3vl2b.jsonConfiguration594 B
pr_split/mathvision.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration604 B
pr_split/mathvision.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration605 B
pr_split/mathvision.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration605 B
pr_split/mathvision.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration602 B
pr_split/mathvision.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration596 B
pr_split/mathvision.claude_opus_4_8.q3vl4b.jsonConfiguration578 B
pr_split/mathvision.gpt_5_6_luna.gemma3_27b.jsonConfiguration322 B
pr_split/mathvision.gpt_5_6_luna.llama4s17b.jsonConfiguration351 B
pr_split/mathvision.gpt_5_6_luna.q35_9b.jsonConfiguration576 B
pr_split/mathvision.gpt_5_6_luna.q3vl2b.jsonConfiguration576 B
pr_split/mathvision.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration603 B
pr_split/mathvision.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration605 B
pr_split/mathvision.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration600 B
pr_split/mathvision.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration602 B
pr_split/mathvision.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration603 B
pr_split/mathvision.gpt_5_6_luna.q3vl4b.jsonConfiguration587 B
pr_split/mathvista.claude_opus_4_8.gemma3_27b.jsonConfiguration335 B
pr_split/mathvista.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration336 B
pr_split/mathvista.claude_opus_4_8.llama4s17b.jsonConfiguration352 B
pr_split/mathvista.claude_opus_4_8.llama4s17b_mc.jsonConfiguration352 B
pr_split/mathvista.claude_opus_4_8.q35_9b.jsonConfiguration568 B
pr_split/mathvista.claude_opus_4_8.q35_9b_mc.jsonConfiguration568 B
pr_split/mathvista.claude_opus_4_8.q3vl2b.jsonConfiguration591 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration591 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration589 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration590 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration604 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration588 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration606 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration606 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_mc.jsonConfiguration577 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration605 B
pr_split/mathvista.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration592 B
pr_split/mathvista.claude_opus_4_8.q3vl4b.jsonConfiguration591 B
pr_split/mathvista.claude_opus_4_8.q3vl4b_mc.jsonConfiguration591 B
pr_split/mathvista.gpt_5_6_luna.gemma3_27b.jsonConfiguration332 B
pr_split/mathvista.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration332 B
pr_split/mathvista.gpt_5_6_luna.llama4s17b.jsonConfiguration349 B
pr_split/mathvista.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration348 B
pr_split/mathvista.gpt_5_6_luna.q35_9b.jsonConfiguration579 B
pr_split/mathvista.gpt_5_6_luna.q35_9b_mc.jsonConfiguration535 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b.jsonConfiguration588 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration602 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration586 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration601 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration585 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration604 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration601 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration588 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration575 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration588 B
pr_split/mathvista.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration586 B
pr_split/mathvista.gpt_5_6_luna.q3vl4b.jsonConfiguration590 B
pr_split/mathvista.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration588 B
pr_split/mmbench.claude_opus_4_8.gemma3_27b.jsonConfiguration329 B
pr_split/mmbench.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration329 B
pr_split/mmbench.claude_opus_4_8.llama4s17b.jsonConfiguration346 B
pr_split/mmbench.claude_opus_4_8.llama4s17b_mc.jsonConfiguration331 B
pr_split/mmbench.claude_opus_4_8.q35_9b.jsonConfiguration578 B
pr_split/mmbench.claude_opus_4_8.q35_9b_mc.jsonConfiguration527 B
pr_split/mmbench.claude_opus_4_8.q3vl2b.jsonConfiguration573 B
pr_split/mmbench.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration601 B
pr_split/mmbench.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration585 B
pr_split/mmbench.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration556 B
pr_split/mmbench.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration585 B
pr_split/mmbench.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration598 B
pr_split/mmbench.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration601 B
pr_split/mmbench.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration585 B
pr_split/mmbench.claude_opus_4_8.q3vl2b_mc.jsonConfiguration587 B
pr_split/mmbench.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration567 B
pr_split/mmbench.claude_opus_4_8.q3vl4b.jsonConfiguration568 B
pr_split/mmbench.claude_opus_4_8.q3vl4b_mc.jsonConfiguration586 B
pr_split/mmbench.gpt_5_6_luna.gemma3_27b.jsonConfiguration327 B
pr_split/mmbench.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration325 B
pr_split/mmbench.gpt_5_6_luna.llama4s17b.jsonConfiguration342 B
pr_split/mmbench.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration328 B
pr_split/mmbench.gpt_5_6_luna.q35_9b.jsonConfiguration575 B
pr_split/mmbench.gpt_5_6_luna.q35_9b_mc.jsonConfiguration509 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b.jsonConfiguration586 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration597 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration583 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration581 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration564 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration583 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration596 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration584 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration569 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration581 B
pr_split/mmbench.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration549 B
pr_split/mmbench.gpt_5_6_luna.q3vl4b.jsonConfiguration582 B
pr_split/mmbench.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration583 B
pr_split/mme.claude_opus_4_8.gemma3_27b.jsonConfiguration328 B
pr_split/mme.claude_opus_4_8.llama4s17b.jsonConfiguration344 B
pr_split/mme.claude_opus_4_8.q35_9b.jsonConfiguration571 B
pr_split/mme.claude_opus_4_8.q3vl2b.jsonConfiguration569 B
pr_split/mme.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration593 B
pr_split/mme.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration594 B
pr_split/mme.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration593 B
pr_split/mme.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration598 B
pr_split/mme.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration582 B
pr_split/mme.claude_opus_4_8.q3vl4b.jsonConfiguration524 B
pr_split/mme.gpt_5_6_luna.gemma3_27b.jsonConfiguration326 B
pr_split/mme.gpt_5_6_luna.llama4s17b.jsonConfiguration343 B
pr_split/mme.gpt_5_6_luna.q35_9b.jsonConfiguration537 B
pr_split/mme.gpt_5_6_luna.q3vl2b.jsonConfiguration568 B
pr_split/mme.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration575 B
pr_split/mme.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration595 B
pr_split/mme.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration591 B
pr_split/mme.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration577 B
pr_split/mme.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration582 B
pr_split/mme.gpt_5_6_luna.q3vl4b.jsonConfiguration578 B
pr_split/mmmu.claude_opus_4_8.gemma3_27b.jsonConfiguration331 B
pr_split/mmmu.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration331 B
pr_split/mmmu.claude_opus_4_8.llama4s17b.jsonConfiguration348 B
pr_split/mmmu.claude_opus_4_8.llama4s17b_mc.jsonConfiguration347 B
pr_split/mmmu.claude_opus_4_8.q35_9b.jsonConfiguration574 B
pr_split/mmmu.claude_opus_4_8.q35_9b_mc.jsonConfiguration573 B
pr_split/mmmu.claude_opus_4_8.q3vl2b.jsonConfiguration584 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration597 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration586 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration588 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration588 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration599 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration598 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration599 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_mc.jsonConfiguration586 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration599 B
pr_split/mmmu.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration598 B
pr_split/mmmu.claude_opus_4_8.q3vl4b.jsonConfiguration571 B
pr_split/mmmu.claude_opus_4_8.q3vl4b_mc.jsonConfiguration584 B
pr_split/mmmu.gpt_5_6_luna.gemma3_27b.jsonConfiguration327 B
pr_split/mmmu.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration327 B
pr_split/mmmu.gpt_5_6_luna.llama4s17b.jsonConfiguration343 B
pr_split/mmmu.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration344 B
pr_split/mmmu.gpt_5_6_luna.q35_9b.jsonConfiguration556 B
pr_split/mmmu.gpt_5_6_luna.q35_9b_mc.jsonConfiguration555 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b.jsonConfiguration584 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration578 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration570 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration596 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration579 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration595 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration597 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration595 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration584 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration537 B
pr_split/mmmu.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration556 B
pr_split/mmmu.gpt_5_6_luna.q3vl4b.jsonConfiguration583 B
pr_split/mmmu.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration582 B
pr_split/mmmu_pro.claude_opus_4_8.gemma3_27b.jsonConfiguration336 B
pr_split/mmmu_pro.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration318 B
pr_split/mmmu_pro.claude_opus_4_8.llama4s17b.jsonConfiguration352 B
pr_split/mmmu_pro.claude_opus_4_8.llama4s17b_mc.jsonConfiguration352 B
pr_split/mmmu_pro.claude_opus_4_8.q35_9b.jsonConfiguration562 B
pr_split/mmmu_pro.claude_opus_4_8.q35_9b_mc.jsonConfiguration577 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b.jsonConfiguration590 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration592 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration603 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration587 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration590 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration549 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration603 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration559 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_mc.jsonConfiguration590 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration605 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration601 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl4b.jsonConfiguration590 B
pr_split/mmmu_pro.claude_opus_4_8.q3vl4b_mc.jsonConfiguration591 B
pr_split/mmmu_pro.gpt_5_6_luna.gemma3_27b.jsonConfiguration332 B
pr_split/mmmu_pro.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration331 B
pr_split/mmmu_pro.gpt_5_6_luna.llama4s17b.jsonConfiguration347 B
pr_split/mmmu_pro.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration348 B
pr_split/mmmu_pro.gpt_5_6_luna.q35_9b.jsonConfiguration559 B
pr_split/mmmu_pro.gpt_5_6_luna.q35_9b_mc.jsonConfiguration561 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b.jsonConfiguration586 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration600 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration600 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration598 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration535 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration555 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration602 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration600 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration586 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration600 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration599 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl4b.jsonConfiguration587 B
pr_split/mmmu_pro.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration587 B
pr_split/mmstar.claude_opus_4_8.gemma3_27b.jsonConfiguration333 B
pr_split/mmstar.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration332 B
pr_split/mmstar.claude_opus_4_8.llama4s17b.jsonConfiguration349 B
pr_split/mmstar.claude_opus_4_8.llama4s17b_mc.jsonConfiguration348 B
pr_split/mmstar.claude_opus_4_8.q35_9b.jsonConfiguration546 B
pr_split/mmstar.claude_opus_4_8.q35_9b_mc.jsonConfiguration559 B
pr_split/mmstar.claude_opus_4_8.q3vl2b.jsonConfiguration586 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration601 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration599 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration598 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration585 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration598 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration547 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration584 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_mc.jsonConfiguration588 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration598 B
pr_split/mmstar.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration584 B
pr_split/mmstar.claude_opus_4_8.q3vl4b.jsonConfiguration542 B
pr_split/mmstar.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration586 B
pr_split/mmstar.claude_opus_4_8.q3vl4b_mc.jsonConfiguration557 B
pr_split/mmstar.gpt_5_6_luna.gemma3_27b.jsonConfiguration330 B
pr_split/mmstar.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration329 B
pr_split/mmstar.gpt_5_6_luna.llama4s17b.jsonConfiguration345 B
pr_split/mmstar.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration345 B
pr_split/mmstar.gpt_5_6_luna.q35_9b.jsonConfiguration573 B
pr_split/mmstar.gpt_5_6_luna.q35_9b_mc.jsonConfiguration559 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b.jsonConfiguration583 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration596 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration581 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration595 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration580 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration594 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration541 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration598 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration569 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration595 B
pr_split/mmstar.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration582 B
pr_split/mmstar.gpt_5_6_luna.q3vl4b.jsonConfiguration542 B
pr_split/mmstar.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration566 B
pr_split/mmstar.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration584 B
pr_split/mmvet.claude_opus_4_8.gemma3_27b.jsonConfiguration333 B
pr_split/mmvet.claude_opus_4_8.llama4s17b.jsonConfiguration334 B
pr_split/mmvet.claude_opus_4_8.q35_9b.jsonConfiguration576 B
pr_split/mmvet.claude_opus_4_8.q3vl2b.jsonConfiguration586 B
pr_split/mmvet.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration601 B
pr_split/mmvet.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration602 B
pr_split/mmvet.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration600 B
pr_split/mmvet.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration600 B
pr_split/mmvet.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration583 B
pr_split/mmvet.claude_opus_4_8.q3vl4b.jsonConfiguration588 B
pr_split/mmvet.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration600 B
pr_split/mmvet.claude_opus_4_8.q3vl4b_vsr1_90.jsonConfiguration584 B
pr_split/mmvet.gpt_5_6_luna.gemma3_27b.jsonConfiguration327 B
pr_split/mmvet.gpt_5_6_luna.llama4s17b.jsonConfiguration330 B
pr_split/mmvet.gpt_5_6_luna.q35_9b.jsonConfiguration560 B
pr_split/mmvet.gpt_5_6_luna.q3vl2b.jsonConfiguration530 B
pr_split/mmvet.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration579 B
pr_split/mmvet.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration596 B
pr_split/mmvet.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration582 B
pr_split/mmvet.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration596 B
pr_split/mmvet.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration583 B
pr_split/mmvet.gpt_5_6_luna.q3vl4b.jsonConfiguration568 B
pr_split/mmvet.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration583 B
pr_split/perceptionbench.claude_opus_4_8.gemma3_27b.jsonConfiguration327 B
pr_split/perceptionbench.claude_opus_4_8.llama4s17b.jsonConfiguration359 B
pr_split/perceptionbench.claude_opus_4_8.q35_9b.jsonConfiguration518 B
pr_split/perceptionbench.claude_opus_4_8.q3vl2b.jsonConfiguration598 B
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration609 B
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration610 B
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration612 B
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration612 B
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration611 B
pr_split/perceptionbench.claude_opus_4_8.q3vl4b.jsonConfiguration582 B
pr_split/perceptionbench.gpt_5_6_luna.gemma3_27b.jsonConfiguration324 B
pr_split/perceptionbench.gpt_5_6_luna.llama4s17b.jsonConfiguration355 B
pr_split/perceptionbench.gpt_5_6_luna.q35_9b.jsonConfiguration571 B
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b.jsonConfiguration597 B
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration608 B
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration594 B
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration608 B
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration608 B
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration606 B
pr_split/perceptionbench.gpt_5_6_luna.q3vl4b.jsonConfiguration595 B
pr_split/realworldqa.claude_opus_4_8.gemma3_27b.jsonConfiguration337 B
pr_split/realworldqa.claude_opus_4_8.llama4s17b.jsonConfiguration337 B
pr_split/realworldqa.claude_opus_4_8.q35_9b.jsonConfiguration521 B
pr_split/realworldqa.claude_opus_4_8.q3vl2b.jsonConfiguration576 B
pr_split/realworldqa.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration604 B
pr_split/realworldqa.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration607 B
pr_split/realworldqa.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration588 B
pr_split/realworldqa.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration605 B
pr_split/realworldqa.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration591 B
pr_split/realworldqa.claude_opus_4_8.q3vl4b.jsonConfiguration592 B
pr_split/realworldqa.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration589 B
pr_split/realworldqa.gpt_5_6_luna.gemma3_27b.jsonConfiguration334 B
pr_split/realworldqa.gpt_5_6_luna.llama4s17b.jsonConfiguration350 B
pr_split/realworldqa.gpt_5_6_luna.q35_9b.jsonConfiguration569 B
pr_split/realworldqa.gpt_5_6_luna.q3vl2b.jsonConfiguration573 B
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration589 B
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration603 B
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration602 B
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration602 B
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration601 B
pr_split/realworldqa.gpt_5_6_luna.q3vl4b.jsonConfiguration584 B
pr_split/realworldqa.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration586 B
pr_split/scienceqa.claude_opus_4_8.gemma3_27b.jsonConfiguration332 B
pr_split/scienceqa.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration331 B
pr_split/scienceqa.claude_opus_4_8.llama4s17b.jsonConfiguration345 B
pr_split/scienceqa.claude_opus_4_8.llama4s17b_mc.jsonConfiguration330 B
pr_split/scienceqa.claude_opus_4_8.q35_9b.jsonConfiguration577 B
pr_split/scienceqa.claude_opus_4_8.q35_9b_mc.jsonConfiguration576 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b.jsonConfiguration588 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration599 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration601 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration598 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration585 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration584 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration586 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration597 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_mc.jsonConfiguration558 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration598 B
pr_split/scienceqa.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration598 B
pr_split/scienceqa.claude_opus_4_8.q3vl4b.jsonConfiguration512 B
pr_split/scienceqa.claude_opus_4_8.q3vl4b_mc.jsonConfiguration507 B
pr_split/scienceqa.gpt_5_6_luna.gemma3_27b.jsonConfiguration313 B
pr_split/scienceqa.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration327 B
pr_split/scienceqa.gpt_5_6_luna.llama4s17b.jsonConfiguration342 B
pr_split/scienceqa.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration327 B
pr_split/scienceqa.gpt_5_6_luna.q35_9b.jsonConfiguration561 B
pr_split/scienceqa.gpt_5_6_luna.q35_9b_mc.jsonConfiguration574 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b.jsonConfiguration568 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration580 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration598 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration595 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration596 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration581 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration596 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration594 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration572 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration596 B
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration596 B
pr_split/scienceqa.gpt_5_6_luna.q3vl4b.jsonConfiguration507 B
pr_split/scienceqa.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration504 B
pr_split/visnumbench.claude_opus_4_8.gemma3_27b.jsonConfiguration339 B
pr_split/visnumbench.claude_opus_4_8.gemma3_27b_mc.jsonConfiguration338 B
pr_split/visnumbench.claude_opus_4_8.llama4s17b.jsonConfiguration356 B
pr_split/visnumbench.claude_opus_4_8.llama4s17b_mc.jsonConfiguration355 B
pr_split/visnumbench.claude_opus_4_8.q35_9b.jsonConfiguration583 B
pr_split/visnumbench.claude_opus_4_8.q35_9b_mc.jsonConfiguration583 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b.jsonConfiguration593 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration592 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration606 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration607 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration591 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration597 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration605 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration606 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_mc.jsonConfiguration537 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration605 B
pr_split/visnumbench.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration606 B
pr_split/visnumbench.claude_opus_4_8.q3vl4b.jsonConfiguration591 B
pr_split/visnumbench.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration606 B
pr_split/visnumbench.claude_opus_4_8.q3vl4b_mc.jsonConfiguration592 B
pr_split/visnumbench.gpt_5_6_luna.gemma3_27b.jsonConfiguration335 B
pr_split/visnumbench.gpt_5_6_luna.gemma3_27b_mc.jsonConfiguration335 B
pr_split/visnumbench.gpt_5_6_luna.llama4s17b.jsonConfiguration351 B
pr_split/visnumbench.gpt_5_6_luna.llama4s17b_mc.jsonConfiguration352 B
pr_split/visnumbench.gpt_5_6_luna.q35_9b.jsonConfiguration581 B
pr_split/visnumbench.gpt_5_6_luna.q35_9b_mc.jsonConfiguration580 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b.jsonConfiguration592 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration603 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration604 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration601 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration603 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration606 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration588 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration604 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration535 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration604 B
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration604 B
pr_split/visnumbench.gpt_5_6_luna.q3vl4b.jsonConfiguration590 B
pr_split/visnumbench.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration603 B
pr_split/visnumbench.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration590 B
results/pr_scores.claude_opus_4_8.q35_9b.jsonConfiguration12.3 KB
results/pr_scores.claude_opus_4_8.q35_9b_mc.jsonConfiguration6.5 KB
results/pr_scores.claude_opus_4_8.q3vl2b.jsonConfiguration12.2 KB
results/pr_scores.claude_opus_4_8.q3vl2b_4bx3_270.jsonConfiguration12.3 KB
results/pr_scores.claude_opus_4_8.q3vl2b_4bx3_270_mc.jsonConfiguration6.5 KB
results/pr_scores.claude_opus_4_8.q3vl2b_4bx_270.jsonConfiguration10.8 KB
results/pr_scores.claude_opus_4_8.q3vl2b_dapo270.jsonConfiguration12.2 KB
results/pr_scores.claude_opus_4_8.q3vl2b_dapo270_mc.jsonConfiguration6.5 KB
results/pr_scores.claude_opus_4_8.q3vl2b_grpo270.jsonConfiguration12.3 KB
results/pr_scores.claude_opus_4_8.q3vl2b_grpo270_mc.jsonConfiguration6.6 KB
results/pr_scores.claude_opus_4_8.q3vl2b_mc.jsonConfiguration6.6 KB
results/pr_scores.claude_opus_4_8.q3vl2b_vsr1_270.jsonConfiguration11.6 KB
results/pr_scores.claude_opus_4_8.q3vl2b_vsr1_270_mc.jsonConfiguration6.5 KB
results/pr_scores.claude_opus_4_8.q3vl4b.jsonConfiguration12.2 KB
results/pr_scores.claude_opus_4_8.q3vl4b_grpo180.jsonConfiguration5.8 KB
results/pr_scores.claude_opus_4_8.q3vl4b_mc.jsonConfiguration6.5 KB
results/pr_scores.gpt_5_6_luna.q35_9b.jsonConfiguration12.0 KB
results/pr_scores.gpt_5_6_luna.q35_9b_mc.jsonConfiguration6.4 KB
results/pr_scores.gpt_5_6_luna.q3vl2b.jsonConfiguration12.0 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_4bx3_270.jsonConfiguration12.1 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_4bx3_270_mc.jsonConfiguration6.4 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_4bx_270.jsonConfiguration10.6 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_dapo270.jsonConfiguration12.0 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_dapo270_mc.jsonConfiguration6.4 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_grpo270.jsonConfiguration12.0 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_grpo270_mc.jsonConfiguration6.4 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_mc.jsonConfiguration6.4 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_vsr1_270.jsonConfiguration12.0 KB
results/pr_scores.gpt_5_6_luna.q3vl2b_vsr1_270_mc.jsonConfiguration6.4 KB
results/pr_scores.gpt_5_6_luna.q3vl4b.jsonConfiguration12.0 KB
results/pr_scores.gpt_5_6_luna.q3vl4b_grpo180.jsonConfiguration5.7 KB
results/pr_scores.gpt_5_6_luna.q3vl4b_mc.jsonConfiguration6.4 KB
results/reasoning_scores.claude_opus_4_8.q3vl2b.jsonConfiguration2.1 KB
baseeval/blink.claude_opus_4_8.q3vl2b.per_sample.jsonlOther314.6 KB
baseeval/chartqa.claude_opus_4_8.q3vl2b.per_sample.jsonlOther175.6 KB
baseeval/hallusionbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther238.9 KB
baseeval/logicvista.claude_opus_4_8.q3vl2b.per_sample.jsonlOther270.1 KB
baseeval/mathverse.claude_opus_4_8.q3vl2b.per_sample.jsonlOther261.6 KB
baseeval/mathvision.claude_opus_4_8.q3vl2b.per_sample.jsonlOther295.5 KB
baseeval/mathvista.claude_opus_4_8.q3vl2b.per_sample.jsonlOther250.1 KB
baseeval/mmbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther278.9 KB
baseeval/mme.claude_opus_4_8.q3vl2b.per_sample.jsonlOther226.6 KB
baseeval/mmmu.claude_opus_4_8.q3vl2b.per_sample.jsonlOther293.1 KB
baseeval/mmmu_pro.claude_opus_4_8.q3vl2b.per_sample.jsonlOther340.2 KB
baseeval/mmstar.claude_opus_4_8.q3vl2b.per_sample.jsonlOther264.8 KB
baseeval/mmvet.claude_opus_4_8.q3vl2b.per_sample.jsonlOther211.0 KB
baseeval/perceptionbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther280.2 KB
baseeval/realworldqa.claude_opus_4_8.q3vl2b.per_sample.jsonlOther215.6 KB
baseeval/scienceqa.claude_opus_4_8.q3vl2b.per_sample.jsonlOther287.7 KB
baseeval/visnumbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther269.7 KB
cond_scores/blink.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther619.2 KB
cond_scores/blink.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther612.5 KB
cond_scores/blink.claude_opus_4_8.llama4s17b.per_sample.jsonlOther636.5 KB
cond_scores/blink.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther628.0 KB
cond_scores/blink.claude_opus_4_8.q35_9b.per_sample.jsonlOther780.7 KB
cond_scores/blink.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther780.6 KB
cond_scores/blink.claude_opus_4_8.q3vl2b.per_sample.jsonlOther776.0 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther717.1 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther724.6 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther776.0 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther780.0 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther778.0 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther777.5 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther778.0 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther776.9 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther776.7 KB
cond_scores/blink.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther776.8 KB
cond_scores/blink.claude_opus_4_8.q3vl4b.per_sample.jsonlOther779.7 KB
cond_scores/blink.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther775.9 KB
cond_scores/blink.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther778.6 KB
cond_scores/blink.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther617.9 KB
cond_scores/blink.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther612.0 KB
cond_scores/blink.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther632.9 KB
cond_scores/blink.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther622.4 KB
cond_scores/blink.gpt_5_6_luna.q35_9b.per_sample.jsonlOther791.4 KB
cond_scores/blink.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther791.0 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther788.0 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther722.5 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther757.0 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther787.5 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther791.5 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther791.1 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther788.4 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther789.0 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther789.0 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther788.1 KB
cond_scores/blink.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther787.9 KB
cond_scores/blink.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther791.0 KB
cond_scores/blink.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther786.4 KB
cond_scores/blink.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther790.1 KB
cond_scores/chartqa.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther487.2 KB
cond_scores/chartqa.claude_opus_4_8.llama4s17b.per_sample.jsonlOther505.6 KB
cond_scores/chartqa.claude_opus_4_8.q35_9b.per_sample.jsonlOther747.9 KB
cond_scores/chartqa.claude_opus_4_8.q3vl2b.per_sample.jsonlOther603.5 KB
cond_scores/chartqa.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther592.0 KB
cond_scores/chartqa.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther618.9 KB
cond_scores/chartqa.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther619.8 KB
cond_scores/chartqa.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther615.7 KB
cond_scores/chartqa.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther607.1 KB
cond_scores/chartqa.claude_opus_4_8.q3vl4b.per_sample.jsonlOther671.9 KB
cond_scores/chartqa.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther603.9 KB
cond_scores/chartqa.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther466.2 KB
cond_scores/chartqa.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther484.2 KB
cond_scores/chartqa.gpt_5_6_luna.q35_9b.per_sample.jsonlOther723.8 KB
cond_scores/chartqa.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther592.7 KB
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther576.9 KB
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther612.7 KB
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther615.9 KB
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther608.8 KB
cond_scores/chartqa.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther600.4 KB
cond_scores/chartqa.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther663.0 KB
cond_scores/chartqa.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther592.0 KB
cond_scores/hallusionbench.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther500.7 KB
cond_scores/hallusionbench.claude_opus_4_8.llama4s17b.per_sample.jsonlOther543.1 KB
cond_scores/hallusionbench.claude_opus_4_8.q35_9b.per_sample.jsonlOther737.5 KB
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther723.0 KB
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther724.2 KB
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther720.9 KB
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther712.3 KB
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther724.3 KB
cond_scores/hallusionbench.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther722.2 KB
cond_scores/hallusionbench.claude_opus_4_8.q3vl4b.per_sample.jsonlOther735.1 KB
cond_scores/hallusionbench.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther714.8 KB
cond_scores/hallusionbench.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther470.5 KB
cond_scores/hallusionbench.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther513.5 KB
cond_scores/hallusionbench.gpt_5_6_luna.q35_9b.per_sample.jsonlOther709.1 KB
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther696.2 KB
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther696.0 KB
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther691.5 KB
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther685.7 KB
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther695.5 KB
cond_scores/hallusionbench.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther693.1 KB
cond_scores/hallusionbench.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther705.5 KB
cond_scores/hallusionbench.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther684.6 KB
cond_scores/logicvista.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther616.7 KB
cond_scores/logicvista.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther612.2 KB
cond_scores/logicvista.claude_opus_4_8.llama4s17b.per_sample.jsonlOther633.9 KB
cond_scores/logicvista.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther634.5 KB
cond_scores/logicvista.claude_opus_4_8.q35_9b.per_sample.jsonlOther761.5 KB
cond_scores/logicvista.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther760.8 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b.per_sample.jsonlOther762.4 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther760.6 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther737.3 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther762.3 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther768.6 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther767.9 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther762.9 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther762.1 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther761.9 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther762.7 KB
cond_scores/logicvista.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther762.0 KB
cond_scores/logicvista.claude_opus_4_8.q3vl4b.per_sample.jsonlOther765.6 KB
cond_scores/logicvista.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther765.6 KB
cond_scores/logicvista.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther765.0 KB
cond_scores/logicvista.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther543.2 KB
cond_scores/logicvista.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther539.7 KB
cond_scores/logicvista.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther561.2 KB
cond_scores/logicvista.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther562.2 KB
cond_scores/logicvista.gpt_5_6_luna.q35_9b.per_sample.jsonlOther688.0 KB
cond_scores/logicvista.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther688.4 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther689.5 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther686.9 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther658.0 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther689.7 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther694.5 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther694.1 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther688.6 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther689.0 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther687.2 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther690.1 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther690.1 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther693.9 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther690.3 KB
cond_scores/logicvista.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther693.0 KB
cond_scores/mathverse.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther605.3 KB
cond_scores/mathverse.claude_opus_4_8.llama4s17b.per_sample.jsonlOther638.4 KB
cond_scores/mathverse.claude_opus_4_8.q35_9b.per_sample.jsonlOther754.0 KB
cond_scores/mathverse.claude_opus_4_8.q3vl2b.per_sample.jsonlOther755.1 KB
cond_scores/mathverse.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther731.6 KB
cond_scores/mathverse.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther752.0 KB
cond_scores/mathverse.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther758.1 KB
cond_scores/mathverse.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther752.6 KB
cond_scores/mathverse.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther751.8 KB
cond_scores/mathverse.claude_opus_4_8.q3vl4b.per_sample.jsonlOther758.3 KB
cond_scores/mathverse.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther554.8 KB
cond_scores/mathverse.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther588.0 KB
cond_scores/mathverse.gpt_5_6_luna.q35_9b.per_sample.jsonlOther703.7 KB
cond_scores/mathverse.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther705.6 KB
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther679.8 KB
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther703.0 KB
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther708.1 KB
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther703.5 KB
cond_scores/mathverse.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther702.6 KB
cond_scores/mathverse.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther709.1 KB
cond_scores/mathvision.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther697.8 KB
cond_scores/mathvision.claude_opus_4_8.llama4s17b.per_sample.jsonlOther710.9 KB
cond_scores/mathvision.claude_opus_4_8.q35_9b.per_sample.jsonlOther786.7 KB
cond_scores/mathvision.claude_opus_4_8.q3vl2b.per_sample.jsonlOther789.2 KB
cond_scores/mathvision.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther786.2 KB
cond_scores/mathvision.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther788.2 KB
cond_scores/mathvision.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther791.9 KB
cond_scores/mathvision.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther787.0 KB
cond_scores/mathvision.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther788.0 KB
cond_scores/mathvision.claude_opus_4_8.q3vl4b.per_sample.jsonlOther791.7 KB
cond_scores/mathvision.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther632.0 KB
cond_scores/mathvision.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther644.8 KB
cond_scores/mathvision.gpt_5_6_luna.q35_9b.per_sample.jsonlOther720.1 KB
cond_scores/mathvision.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther722.2 KB
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther719.7 KB
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther721.6 KB
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther726.4 KB
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther720.5 KB
cond_scores/mathvision.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther722.0 KB
cond_scores/mathvision.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther725.4 KB
cond_scores/mathvista.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther625.5 KB
cond_scores/mathvista.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther629.4 KB
cond_scores/mathvista.claude_opus_4_8.llama4s17b.per_sample.jsonlOther652.0 KB
cond_scores/mathvista.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther658.8 KB
cond_scores/mathvista.claude_opus_4_8.q35_9b.per_sample.jsonlOther743.5 KB
cond_scores/mathvista.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther742.8 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b.per_sample.jsonlOther732.5 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther731.3 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther717.1 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther731.9 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther732.8 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther734.1 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther731.4 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther733.9 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther735.5 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther732.5 KB
cond_scores/mathvista.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther734.4 KB
cond_scores/mathvista.claude_opus_4_8.q3vl4b.per_sample.jsonlOther738.1 KB
cond_scores/mathvista.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther734.3 KB
cond_scores/mathvista.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther573.6 KB
cond_scores/mathvista.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther576.5 KB
cond_scores/mathvista.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther601.2 KB
cond_scores/mathvista.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther607.6 KB
cond_scores/mathvista.gpt_5_6_luna.q35_9b.per_sample.jsonlOther692.9 KB
cond_scores/mathvista.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther693.4 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther683.1 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther683.8 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther674.0 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther684.3 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther684.6 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther686.3 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther682.3 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther684.2 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther685.2 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther682.8 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther684.3 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther690.8 KB
cond_scores/mathvista.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther687.6 KB
cond_scores/mmbench.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther532.1 KB
cond_scores/mmbench.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther531.4 KB
cond_scores/mmbench.claude_opus_4_8.llama4s17b.per_sample.jsonlOther553.4 KB
cond_scores/mmbench.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther557.2 KB
cond_scores/mmbench.claude_opus_4_8.q35_9b.per_sample.jsonlOther767.9 KB
cond_scores/mmbench.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther768.1 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther762.6 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther678.0 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther726.2 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther756.8 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther760.1 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther760.2 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther763.7 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther763.8 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther763.9 KB
cond_scores/mmbench.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther763.6 KB
cond_scores/mmbench.claude_opus_4_8.q3vl4b.per_sample.jsonlOther771.8 KB
cond_scores/mmbench.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther769.9 KB
cond_scores/mmbench.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther515.2 KB
cond_scores/mmbench.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther514.5 KB
cond_scores/mmbench.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther536.2 KB
cond_scores/mmbench.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther539.6 KB
cond_scores/mmbench.gpt_5_6_luna.q35_9b.per_sample.jsonlOther750.9 KB
cond_scores/mmbench.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther751.0 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther745.6 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther665.0 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther726.9 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther739.8 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther744.9 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther744.8 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther746.2 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther747.1 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther746.5 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther745.5 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther746.2 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther755.1 KB
cond_scores/mmbench.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther754.0 KB
cond_scores/mme.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther469.7 KB
cond_scores/mme.claude_opus_4_8.llama4s17b.per_sample.jsonlOther514.2 KB
cond_scores/mme.claude_opus_4_8.q35_9b.per_sample.jsonlOther716.5 KB
cond_scores/mme.claude_opus_4_8.q3vl2b.per_sample.jsonlOther682.3 KB
cond_scores/mme.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther682.9 KB
cond_scores/mme.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther677.2 KB
cond_scores/mme.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther634.2 KB
cond_scores/mme.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther682.2 KB
cond_scores/mme.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther677.1 KB
cond_scores/mme.claude_opus_4_8.q3vl4b.per_sample.jsonlOther707.0 KB
cond_scores/mme.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther475.1 KB
cond_scores/mme.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther518.9 KB
cond_scores/mme.gpt_5_6_luna.q35_9b.per_sample.jsonlOther729.2 KB
cond_scores/mme.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther697.0 KB
cond_scores/mme.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther704.3 KB
cond_scores/mme.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther694.1 KB
cond_scores/mme.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther647.3 KB
cond_scores/mme.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther697.0 KB
cond_scores/mme.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther690.7 KB
cond_scores/mme.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther721.8 KB
cond_scores/mmmu.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther624.6 KB
cond_scores/mmmu.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther624.9 KB
cond_scores/mmmu.claude_opus_4_8.llama4s17b.per_sample.jsonlOther631.7 KB
cond_scores/mmmu.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther633.1 KB
cond_scores/mmmu.claude_opus_4_8.q35_9b.per_sample.jsonlOther777.2 KB
cond_scores/mmmu.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther777.4 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b.per_sample.jsonlOther778.3 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther743.1 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther757.2 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther777.6 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther783.3 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther783.5 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther777.8 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther777.5 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther777.4 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther777.8 KB
cond_scores/mmmu.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther777.1 KB
cond_scores/mmmu.claude_opus_4_8.q3vl4b.per_sample.jsonlOther782.4 KB
cond_scores/mmmu.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther782.4 KB
cond_scores/mmmu.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther598.2 KB
cond_scores/mmmu.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther599.3 KB
cond_scores/mmmu.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther606.2 KB
cond_scores/mmmu.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther607.7 KB
cond_scores/mmmu.gpt_5_6_luna.q35_9b.per_sample.jsonlOther756.1 KB
cond_scores/mmmu.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther755.9 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther756.7 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther717.5 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther743.6 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther756.0 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther762.2 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther762.6 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther756.0 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther756.0 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther756.1 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther756.4 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther756.1 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther762.3 KB
cond_scores/mmmu.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther762.0 KB
cond_scores/mmmu_pro.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther703.9 KB
cond_scores/mmmu_pro.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther693.2 KB
cond_scores/mmmu_pro.claude_opus_4_8.llama4s17b.per_sample.jsonlOther698.6 KB
cond_scores/mmmu_pro.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther700.1 KB
cond_scores/mmmu_pro.claude_opus_4_8.q35_9b.per_sample.jsonlOther820.6 KB
cond_scores/mmmu_pro.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther820.6 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b.per_sample.jsonlOther821.8 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther801.2 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther801.5 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther820.8 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther825.9 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther826.4 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther821.3 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther821.2 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther821.5 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther821.3 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther821.2 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl4b.per_sample.jsonlOther824.6 KB
cond_scores/mmmu_pro.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther824.3 KB
cond_scores/mmmu_pro.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther673.6 KB
cond_scores/mmmu_pro.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther662.8 KB
cond_scores/mmmu_pro.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther669.3 KB
cond_scores/mmmu_pro.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther671.1 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q35_9b.per_sample.jsonlOther797.6 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther797.8 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther798.5 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther780.0 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther786.9 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther797.5 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther802.6 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther803.7 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther797.9 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther797.8 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther798.0 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther797.7 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther797.5 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther802.2 KB
cond_scores/mmmu_pro.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther801.2 KB
cond_scores/mmstar.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther562.0 KB
cond_scores/mmstar.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther549.0 KB
cond_scores/mmstar.claude_opus_4_8.llama4s17b.per_sample.jsonlOther577.8 KB
cond_scores/mmstar.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther584.0 KB
cond_scores/mmstar.claude_opus_4_8.q35_9b.per_sample.jsonlOther753.4 KB
cond_scores/mmstar.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther751.9 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b.per_sample.jsonlOther748.8 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther693.4 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther705.3 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther744.4 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther744.6 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther745.8 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther745.3 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther747.4 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther750.4 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther747.3 KB
cond_scores/mmstar.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther747.3 KB
cond_scores/mmstar.claude_opus_4_8.q3vl4b.per_sample.jsonlOther755.6 KB
cond_scores/mmstar.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther763.4 KB
cond_scores/mmstar.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther753.4 KB
cond_scores/mmstar.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther536.4 KB
cond_scores/mmstar.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther521.7 KB
cond_scores/mmstar.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther549.9 KB
cond_scores/mmstar.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther556.9 KB
cond_scores/mmstar.gpt_5_6_luna.q35_9b.per_sample.jsonlOther725.4 KB
cond_scores/mmstar.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther725.8 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther721.9 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther666.4 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther696.8 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther717.4 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther717.9 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther719.8 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther718.5 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther719.1 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther721.9 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther719.9 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther719.9 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther729.8 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther729.5 KB
cond_scores/mmstar.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther727.8 KB
cond_scores/mmvet.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther513.5 KB
cond_scores/mmvet.claude_opus_4_8.llama4s17b.per_sample.jsonlOther586.2 KB
cond_scores/mmvet.claude_opus_4_8.q35_9b.per_sample.jsonlOther746.8 KB
cond_scores/mmvet.claude_opus_4_8.q3vl2b.per_sample.jsonlOther589.6 KB
cond_scores/mmvet.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther602.4 KB
cond_scores/mmvet.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther618.1 KB
cond_scores/mmvet.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther587.1 KB
cond_scores/mmvet.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther620.5 KB
cond_scores/mmvet.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther620.3 KB
cond_scores/mmvet.claude_opus_4_8.q3vl4b.per_sample.jsonlOther619.6 KB
cond_scores/mmvet.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther587.6 KB
cond_scores/mmvet.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther513.7 KB
cond_scores/mmvet.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther589.5 KB
cond_scores/mmvet.gpt_5_6_luna.q35_9b.per_sample.jsonlOther755.7 KB
cond_scores/mmvet.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther605.2 KB
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther610.8 KB
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther630.0 KB
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther599.0 KB
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther632.0 KB
cond_scores/mmvet.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther634.5 KB
cond_scores/mmvet.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther634.6 KB
cond_scores/mmvet.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther589.7 KB
cond_scores/perceptionbench.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther616.9 KB
cond_scores/perceptionbench.claude_opus_4_8.llama4s17b.per_sample.jsonlOther695.4 KB
cond_scores/perceptionbench.claude_opus_4_8.q35_9b.per_sample.jsonlOther750.5 KB
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther734.5 KB
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther717.9 KB
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther732.9 KB
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther724.9 KB
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther738.1 KB
cond_scores/perceptionbench.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther736.2 KB
cond_scores/perceptionbench.claude_opus_4_8.q3vl4b.per_sample.jsonlOther747.1 KB
cond_scores/perceptionbench.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther544.2 KB
cond_scores/perceptionbench.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther626.5 KB
cond_scores/perceptionbench.gpt_5_6_luna.q35_9b.per_sample.jsonlOther693.8 KB
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther680.1 KB
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther666.4 KB
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther679.9 KB
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther671.3 KB
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther681.3 KB
cond_scores/perceptionbench.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther680.9 KB
cond_scores/perceptionbench.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther691.1 KB
cond_scores/realworldqa.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther499.9 KB
cond_scores/realworldqa.claude_opus_4_8.llama4s17b.per_sample.jsonlOther543.5 KB
cond_scores/realworldqa.claude_opus_4_8.q35_9b.per_sample.jsonlOther738.1 KB
cond_scores/realworldqa.claude_opus_4_8.q3vl2b.per_sample.jsonlOther649.1 KB
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther499.5 KB
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther633.1 KB
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther621.7 KB
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther639.0 KB
cond_scores/realworldqa.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther611.6 KB
cond_scores/realworldqa.claude_opus_4_8.q3vl4b.per_sample.jsonlOther695.9 KB
cond_scores/realworldqa.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther415.0 KB
cond_scores/realworldqa.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther503.6 KB
cond_scores/realworldqa.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther546.4 KB
cond_scores/realworldqa.gpt_5_6_luna.q35_9b.per_sample.jsonlOther748.7 KB
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther654.8 KB
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther507.2 KB
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther636.9 KB
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther637.4 KB
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther643.1 KB
cond_scores/realworldqa.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther616.8 KB
cond_scores/realworldqa.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther710.5 KB
cond_scores/realworldqa.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther413.6 KB
cond_scores/scienceqa.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther535.4 KB
cond_scores/scienceqa.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther528.4 KB
cond_scores/scienceqa.claude_opus_4_8.llama4s17b.per_sample.jsonlOther543.2 KB
cond_scores/scienceqa.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther543.7 KB
cond_scores/scienceqa.claude_opus_4_8.q35_9b.per_sample.jsonlOther777.8 KB
cond_scores/scienceqa.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther778.4 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b.per_sample.jsonlOther775.7 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther717.1 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther741.7 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther774.3 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther771.2 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther773.5 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther778.3 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther778.9 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther777.4 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther775.8 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther777.1 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl4b.per_sample.jsonlOther780.8 KB
cond_scores/scienceqa.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther779.9 KB
cond_scores/scienceqa.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther522.0 KB
cond_scores/scienceqa.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther514.5 KB
cond_scores/scienceqa.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther529.5 KB
cond_scores/scienceqa.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther530.0 KB
cond_scores/scienceqa.gpt_5_6_luna.q35_9b.per_sample.jsonlOther764.9 KB
cond_scores/scienceqa.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther763.8 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther761.9 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther696.1 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther728.5 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther760.3 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther756.0 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther759.3 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther763.8 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther764.9 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther763.2 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther761.4 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther763.0 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther768.4 KB
cond_scores/scienceqa.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther767.2 KB
cond_scores/visnumbench.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther634.0 KB
cond_scores/visnumbench.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther625.7 KB
cond_scores/visnumbench.claude_opus_4_8.llama4s17b.per_sample.jsonlOther654.8 KB
cond_scores/visnumbench.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther652.2 KB
cond_scores/visnumbench.claude_opus_4_8.q35_9b.per_sample.jsonlOther757.4 KB
cond_scores/visnumbench.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther754.9 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther759.3 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther741.2 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther739.5 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther758.2 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther765.7 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther766.0 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther759.0 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther758.5 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther758.5 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther759.1 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther758.1 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl4b.per_sample.jsonlOther764.5 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther761.6 KB
cond_scores/visnumbench.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther764.1 KB
cond_scores/visnumbench.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther599.7 KB
cond_scores/visnumbench.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther591.2 KB
cond_scores/visnumbench.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther620.0 KB
cond_scores/visnumbench.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther617.4 KB
cond_scores/visnumbench.gpt_5_6_luna.q35_9b.per_sample.jsonlOther723.9 KB
cond_scores/visnumbench.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther723.6 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther724.5 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther707.3 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther718.7 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther723.1 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther731.5 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther732.2 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther724.3 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther723.1 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther723.8 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther724.9 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther723.5 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther729.1 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther727.3 KB
cond_scores/visnumbench.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther728.9 KB
descriptions/blink.claude_opus_4_8.jsonlOther413.4 KB
descriptions/blink.gpt_5_6_luna.jsonlOther538.2 KB
descriptions/chartqa.claude_opus_4_8.jsonlOther363.8 KB
descriptions/chartqa.gpt_5_6_luna.jsonlOther355.2 KB
descriptions/hallusionbench.claude_opus_4_8.jsonlOther386.2 KB
descriptions/hallusionbench.gpt_5_6_luna.jsonlOther335.9 KB
descriptions/logicvista.claude_opus_4_8.jsonlOther364.8 KB
descriptions/logicvista.gpt_5_6_luna.jsonlOther245.3 KB
descriptions/mathverse.claude_opus_4_8.jsonlOther411.3 KB
descriptions/mathverse.gpt_5_6_luna.jsonlOther289.8 KB
descriptions/mathvision.claude_opus_4_8.jsonlOther409.5 KB
descriptions/mathvision.gpt_5_6_luna.jsonlOther250.6 KB
descriptions/mathvista.claude_opus_4_8.jsonlOther379.4 KB
descriptions/mathvista.gpt_5_6_luna.jsonlOther298.4 KB
descriptions/mmbench.claude_opus_4_8.jsonlOther406.8 KB
descriptions/mmbench.gpt_5_6_luna.jsonlOther481.6 KB
descriptions/mme.claude_opus_4_8.jsonlOther408.4 KB
descriptions/mme.gpt_5_6_luna.jsonlOther557.5 KB
descriptions/mmmu.claude_opus_4_8.jsonlOther394.4 KB
descriptions/mmmu.gpt_5_6_luna.jsonlOther380.0 KB
descriptions/mmmu_pro.claude_opus_4_8.jsonlOther387.8 KB
descriptions/mmmu_pro.gpt_5_6_luna.jsonlOther343.9 KB
descriptions/mmstar.claude_opus_4_8.jsonlOther405.6 KB
descriptions/mmstar.gpt_5_6_luna.jsonlOther409.5 KB
descriptions/mmvet.claude_opus_4_8.jsonlOther394.2 KB
descriptions/mmvet.gpt_5_6_luna.jsonlOther498.8 KB
descriptions/perceptionbench.claude_opus_4_8.jsonlOther400.7 KB
descriptions/perceptionbench.gpt_5_6_luna.jsonlOther321.2 KB
descriptions/realworldqa.claude_opus_4_8.jsonlOther422.8 KB
descriptions/realworldqa.gpt_5_6_luna.jsonlOther583.7 KB
descriptions/scienceqa.claude_opus_4_8.jsonlOther404.1 KB
descriptions/scienceqa.gpt_5_6_luna.jsonlOther413.1 KB
descriptions/visnumbench.claude_opus_4_8.jsonlOther407.1 KB
descriptions/visnumbench.gpt_5_6_luna.jsonlOther342.9 KB
logs/eval-para-api-gemma3_27b.logOther271.1 KB
logs/eval-para-api-llama4s17b.logOther129.1 KB
logs/para-q3vl2b_4bx3_270.logOther42.4 MB 0ff53a8448cf
logs/para-q3vl2b_4bx_270.logOther18.0 MB a68edec15960
logs/para-q3vl2b_dapo270.logOther1.8 MB b7e797398943
logs/para-q3vl2b_grpo270.logOther3.1 MB ca83911f768c
logs/para-q3vl2b_vsr1_270.logOther91.1 KB 95383f6dfba6
logs/para-q3vl4b_grpo180.logOther12.6 MB eabf03709ff1
logs/rscore-4b-claude_opus_4_8.logOther1.8 MB
logs/rscore-4b-gpt_5_6_luna.logOther12.8 MB e3685a46ab85
logs/rscore-9b-claude_opus_4_8.logOther15.6 MB 2a1627385352
logs/rscore-9b-gpt_5_6_luna.logOther13.1 MB f8a29c9654bc
logs/rscore-mcfix-q35_9b_mc.logOther15.0 MB a6d63026d9f0
logs/rscore-mcfix-q3vl2b_mc.logOther7.5 MB
logs/rscore-mcfix-q3vl4b_mc.logOther49.2 KB 5007de9e40f8
logs/selfdesc-9b-blink_visnumbench.logOther108.0 KB
logs/selfdesc-9b-hallusionbench_mmvet_chartqa_mme_mmbench.logOther325.7 KB
logs/selfdesc-9b-scienceqa_perceptionbench_mathvista_mmmu.logOther259.8 KB
logs/selfdesc-9b-visnumbench_realworldqa_blink_mmstar_log.logOther204.2 KB
pr_split/blink.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther153.6 KB
pr_split/blink.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther142.8 KB
pr_split/blink.claude_opus_4_8.llama4s17b.per_sample.jsonlOther118.7 KB
pr_split/blink.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther105.7 KB
pr_split/blink.claude_opus_4_8.q35_9b.per_sample.jsonlOther109.2 KB
pr_split/blink.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther115.6 KB
pr_split/blink.claude_opus_4_8.q3vl2b.per_sample.jsonlOther147.7 KB
pr_split/blink.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther142.7 KB
pr_split/blink.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther153.3 KB
pr_split/blink.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther142.8 KB
pr_split/blink.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther148.9 KB
pr_split/blink.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther143.6 KB
pr_split/blink.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther134.8 KB
pr_split/blink.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther136.2 KB
pr_split/blink.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther136.0 KB
pr_split/blink.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther141.5 KB
pr_split/blink.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther144.2 KB
pr_split/blink.claude_opus_4_8.q3vl4b.per_sample.jsonlOther100.2 KB
pr_split/blink.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther119.9 KB
pr_split/blink.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther95.6 KB
pr_split/blink.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther107.6 KB
pr_split/blink.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther102.2 KB
pr_split/blink.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther88.4 KB
pr_split/blink.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther77.4 KB
pr_split/blink.gpt_5_6_luna.q35_9b.per_sample.jsonlOther80.8 KB
pr_split/blink.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther84.5 KB
pr_split/blink.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther112.2 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther106.3 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther114.5 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther110.1 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther114.3 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther111.9 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther100.4 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther103.8 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther105.0 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther107.9 KB
pr_split/blink.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther108.9 KB
pr_split/blink.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther76.7 KB
pr_split/blink.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther94.2 KB
pr_split/blink.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther71.7 KB
pr_split/chartqa.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther62.0 KB
pr_split/chartqa.claude_opus_4_8.llama4s17b.per_sample.jsonlOther40.0 KB
pr_split/chartqa.claude_opus_4_8.q35_9b.per_sample.jsonlOther77.5 KB
pr_split/chartqa.claude_opus_4_8.q3vl2b.per_sample.jsonlOther53.8 KB
pr_split/chartqa.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther73.2 KB
pr_split/chartqa.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther83.0 KB
pr_split/chartqa.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther96.4 KB
pr_split/chartqa.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther66.7 KB
pr_split/chartqa.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther54.7 KB
pr_split/chartqa.claude_opus_4_8.q3vl4b.per_sample.jsonlOther58.2 KB
pr_split/chartqa.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther57.4 KB
pr_split/chartqa.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther55.0 KB
pr_split/chartqa.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther34.8 KB
pr_split/chartqa.gpt_5_6_luna.q35_9b.per_sample.jsonlOther71.0 KB
pr_split/chartqa.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther48.1 KB
pr_split/chartqa.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther66.5 KB
pr_split/chartqa.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther73.8 KB
pr_split/chartqa.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther86.1 KB
pr_split/chartqa.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther59.7 KB
pr_split/chartqa.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther48.1 KB
pr_split/chartqa.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther51.7 KB
pr_split/chartqa.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther52.2 KB
pr_split/hallusionbench.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther69.6 KB
pr_split/hallusionbench.claude_opus_4_8.llama4s17b.per_sample.jsonlOther66.9 KB
pr_split/hallusionbench.claude_opus_4_8.q35_9b.per_sample.jsonlOther105.9 KB
pr_split/hallusionbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther79.0 KB
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther72.8 KB
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther72.7 KB
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther90.6 KB
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther84.7 KB
pr_split/hallusionbench.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther71.8 KB
pr_split/hallusionbench.claude_opus_4_8.q3vl4b.per_sample.jsonlOther76.5 KB
pr_split/hallusionbench.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther61.8 KB
pr_split/hallusionbench.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther49.0 KB
pr_split/hallusionbench.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther47.5 KB
pr_split/hallusionbench.gpt_5_6_luna.q35_9b.per_sample.jsonlOther73.8 KB
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther56.5 KB
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther51.4 KB
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther51.4 KB
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther65.8 KB
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther60.2 KB
pr_split/hallusionbench.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther52.0 KB
pr_split/hallusionbench.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther54.4 KB
pr_split/hallusionbench.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther44.8 KB
pr_split/logicvista.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther142.6 KB
pr_split/logicvista.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther137.8 KB
pr_split/logicvista.claude_opus_4_8.llama4s17b.per_sample.jsonlOther157.2 KB
pr_split/logicvista.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther160.7 KB
pr_split/logicvista.claude_opus_4_8.q35_9b.per_sample.jsonlOther157.3 KB
pr_split/logicvista.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther152.6 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b.per_sample.jsonlOther142.5 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther150.7 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther164.0 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther161.0 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther174.8 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther168.9 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther153.4 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther140.8 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther147.6 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther163.2 KB
pr_split/logicvista.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther148.2 KB
pr_split/logicvista.claude_opus_4_8.q3vl4b.per_sample.jsonlOther122.8 KB
pr_split/logicvista.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther124.5 KB
pr_split/logicvista.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther128.2 KB
pr_split/logicvista.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther105.9 KB
pr_split/logicvista.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther103.1 KB
pr_split/logicvista.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther117.0 KB
pr_split/logicvista.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther119.6 KB
pr_split/logicvista.gpt_5_6_luna.q35_9b.per_sample.jsonlOther122.8 KB
pr_split/logicvista.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther118.2 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther110.9 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther114.9 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther126.0 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther126.0 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther136.7 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther136.7 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther119.6 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther109.8 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther119.2 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther124.8 KB
pr_split/logicvista.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther117.8 KB
pr_split/logicvista.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther92.1 KB
pr_split/logicvista.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther93.0 KB
pr_split/logicvista.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther98.1 KB
pr_split/mathverse.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther148.9 KB
pr_split/mathverse.claude_opus_4_8.llama4s17b.per_sample.jsonlOther149.9 KB
pr_split/mathverse.claude_opus_4_8.q35_9b.per_sample.jsonlOther183.9 KB
pr_split/mathverse.claude_opus_4_8.q3vl2b.per_sample.jsonlOther191.8 KB
pr_split/mathverse.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther170.3 KB
pr_split/mathverse.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther169.2 KB
pr_split/mathverse.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther174.0 KB
pr_split/mathverse.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther168.4 KB
pr_split/mathverse.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther174.2 KB
pr_split/mathverse.claude_opus_4_8.q3vl4b.per_sample.jsonlOther152.9 KB
pr_split/mathverse.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther130.5 KB
pr_split/mathverse.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther130.6 KB
pr_split/mathverse.gpt_5_6_luna.q35_9b.per_sample.jsonlOther162.1 KB
pr_split/mathverse.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther169.1 KB
pr_split/mathverse.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther148.8 KB
pr_split/mathverse.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther149.8 KB
pr_split/mathverse.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther153.3 KB
pr_split/mathverse.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther148.1 KB
pr_split/mathverse.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther154.2 KB
pr_split/mathverse.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther135.0 KB
pr_split/mathvision.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther215.4 KB
pr_split/mathvision.claude_opus_4_8.llama4s17b.per_sample.jsonlOther225.3 KB
pr_split/mathvision.claude_opus_4_8.q35_9b.per_sample.jsonlOther198.3 KB
pr_split/mathvision.claude_opus_4_8.q3vl2b.per_sample.jsonlOther223.8 KB
pr_split/mathvision.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther223.2 KB
pr_split/mathvision.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther224.0 KB
pr_split/mathvision.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther246.3 KB
pr_split/mathvision.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther232.6 KB
pr_split/mathvision.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther212.7 KB
pr_split/mathvision.claude_opus_4_8.q3vl4b.per_sample.jsonlOther177.0 KB
pr_split/mathvision.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther167.0 KB
pr_split/mathvision.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther170.7 KB
pr_split/mathvision.gpt_5_6_luna.q35_9b.per_sample.jsonlOther159.6 KB
pr_split/mathvision.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther179.8 KB
pr_split/mathvision.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther174.6 KB
pr_split/mathvision.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther180.9 KB
pr_split/mathvision.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther194.1 KB
pr_split/mathvision.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther183.6 KB
pr_split/mathvision.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther173.1 KB
pr_split/mathvision.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther139.5 KB
pr_split/mathvista.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther200.3 KB
pr_split/mathvista.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther208.2 KB
pr_split/mathvista.claude_opus_4_8.llama4s17b.per_sample.jsonlOther179.9 KB
pr_split/mathvista.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther187.8 KB
pr_split/mathvista.claude_opus_4_8.q35_9b.per_sample.jsonlOther174.6 KB
pr_split/mathvista.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther167.7 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b.per_sample.jsonlOther205.4 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther200.4 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther203.6 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther199.7 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther202.8 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther204.9 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther198.6 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther199.8 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther201.5 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther199.3 KB
pr_split/mathvista.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther202.3 KB
pr_split/mathvista.claude_opus_4_8.q3vl4b.per_sample.jsonlOther185.6 KB
pr_split/mathvista.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther184.9 KB
pr_split/mathvista.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther171.2 KB
pr_split/mathvista.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther178.0 KB
pr_split/mathvista.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther154.8 KB
pr_split/mathvista.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther161.1 KB
pr_split/mathvista.gpt_5_6_luna.q35_9b.per_sample.jsonlOther154.5 KB
pr_split/mathvista.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther149.3 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther175.8 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther173.6 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther177.2 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther172.7 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther174.9 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther177.6 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther171.8 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther173.2 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther174.6 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther173.2 KB
pr_split/mathvista.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther174.3 KB
pr_split/mathvista.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther163.1 KB
pr_split/mathvista.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther163.7 KB
pr_split/mmbench.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther42.6 KB
pr_split/mmbench.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther36.6 KB
pr_split/mmbench.claude_opus_4_8.llama4s17b.per_sample.jsonlOther32.6 KB
pr_split/mmbench.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther35.8 KB
pr_split/mmbench.claude_opus_4_8.q35_9b.per_sample.jsonlOther58.6 KB
pr_split/mmbench.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther48.5 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther61.9 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther49.2 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther41.9 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther43.4 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther43.6 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther40.1 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther51.5 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther41.7 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther53.0 KB
pr_split/mmbench.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther38.6 KB
pr_split/mmbench.claude_opus_4_8.q3vl4b.per_sample.jsonlOther53.3 KB
pr_split/mmbench.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther51.6 KB
pr_split/mmbench.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther32.0 KB
pr_split/mmbench.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther28.9 KB
pr_split/mmbench.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther25.9 KB
pr_split/mmbench.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther28.8 KB
pr_split/mmbench.gpt_5_6_luna.q35_9b.per_sample.jsonlOther46.4 KB
pr_split/mmbench.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther39.2 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther46.4 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther37.2 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther32.4 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther33.8 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther34.0 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther31.7 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther39.1 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther33.5 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther41.2 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther33.7 KB
pr_split/mmbench.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther29.3 KB
pr_split/mmbench.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther41.0 KB
pr_split/mmbench.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther40.9 KB
pr_split/mme.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther62.2 KB
pr_split/mme.claude_opus_4_8.llama4s17b.per_sample.jsonlOther49.4 KB
pr_split/mme.claude_opus_4_8.q35_9b.per_sample.jsonlOther32.2 KB
pr_split/mme.claude_opus_4_8.q3vl2b.per_sample.jsonlOther70.0 KB
pr_split/mme.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther49.5 KB
pr_split/mme.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther61.3 KB
pr_split/mme.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther61.2 KB
pr_split/mme.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther69.2 KB
pr_split/mme.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther78.3 KB
pr_split/mme.claude_opus_4_8.q3vl4b.per_sample.jsonlOther46.1 KB
pr_split/mme.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther38.9 KB
pr_split/mme.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther36.7 KB
pr_split/mme.gpt_5_6_luna.q35_9b.per_sample.jsonlOther24.5 KB
pr_split/mme.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther51.0 KB
pr_split/mme.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther38.1 KB
pr_split/mme.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther46.5 KB
pr_split/mme.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther46.3 KB
pr_split/mme.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther51.4 KB
pr_split/mme.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther59.1 KB
pr_split/mme.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther37.7 KB
pr_split/mmmu.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther126.7 KB
pr_split/mmmu.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther128.3 KB
pr_split/mmmu.claude_opus_4_8.llama4s17b.per_sample.jsonlOther128.2 KB
pr_split/mmmu.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther128.6 KB
pr_split/mmmu.claude_opus_4_8.q35_9b.per_sample.jsonlOther157.4 KB
pr_split/mmmu.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther160.2 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b.per_sample.jsonlOther175.2 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther153.2 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther179.6 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther153.8 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther148.6 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther159.8 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther176.2 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther178.5 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther175.7 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther167.4 KB
pr_split/mmmu.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther161.0 KB
pr_split/mmmu.claude_opus_4_8.q3vl4b.per_sample.jsonlOther152.9 KB
pr_split/mmmu.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther154.6 KB
pr_split/mmmu.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther98.7 KB
pr_split/mmmu.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther99.4 KB
pr_split/mmmu.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther99.5 KB
pr_split/mmmu.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther100.4 KB
pr_split/mmmu.gpt_5_6_luna.q35_9b.per_sample.jsonlOther134.0 KB
pr_split/mmmu.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther138.8 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther142.8 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther128.5 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther150.5 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther126.5 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther127.6 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther132.1 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther149.6 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther151.9 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther148.1 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther144.0 KB
pr_split/mmmu.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther140.0 KB
pr_split/mmmu.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther125.3 KB
pr_split/mmmu.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther126.8 KB
pr_split/mmmu_pro.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther172.1 KB
pr_split/mmmu_pro.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther155.6 KB
pr_split/mmmu_pro.claude_opus_4_8.llama4s17b.per_sample.jsonlOther156.1 KB
pr_split/mmmu_pro.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther158.0 KB
pr_split/mmmu_pro.claude_opus_4_8.q35_9b.per_sample.jsonlOther98.0 KB
pr_split/mmmu_pro.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther94.3 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b.per_sample.jsonlOther146.6 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther202.2 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther189.2 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther160.3 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther211.2 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther219.6 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther170.3 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther167.2 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther151.5 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther171.3 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther151.7 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl4b.per_sample.jsonlOther126.3 KB
pr_split/mmmu_pro.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther123.5 KB
pr_split/mmmu_pro.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther133.1 KB
pr_split/mmmu_pro.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther122.5 KB
pr_split/mmmu_pro.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther124.1 KB
pr_split/mmmu_pro.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther127.0 KB
pr_split/mmmu_pro.gpt_5_6_luna.q35_9b.per_sample.jsonlOther80.6 KB
pr_split/mmmu_pro.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther79.9 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther125.0 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther167.2 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther159.5 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther131.5 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther174.7 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther180.4 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther141.2 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther140.1 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther130.9 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther140.9 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther125.6 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther102.9 KB
pr_split/mmmu_pro.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther104.4 KB
pr_split/mmstar.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther117.2 KB
pr_split/mmstar.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther99.1 KB
pr_split/mmstar.claude_opus_4_8.llama4s17b.per_sample.jsonlOther86.6 KB
pr_split/mmstar.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther91.7 KB
pr_split/mmstar.claude_opus_4_8.q35_9b.per_sample.jsonlOther110.4 KB
pr_split/mmstar.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther106.9 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b.per_sample.jsonlOther125.8 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther100.0 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther113.9 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther122.6 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther106.9 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther110.9 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther122.3 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther115.8 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther126.6 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther110.0 KB
pr_split/mmstar.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther123.9 KB
pr_split/mmstar.claude_opus_4_8.q3vl4b.per_sample.jsonlOther86.0 KB
pr_split/mmstar.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther84.1 KB
pr_split/mmstar.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther92.5 KB
pr_split/mmstar.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther93.1 KB
pr_split/mmstar.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther79.4 KB
pr_split/mmstar.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther68.2 KB
pr_split/mmstar.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther75.1 KB
pr_split/mmstar.gpt_5_6_luna.q35_9b.per_sample.jsonlOther89.0 KB
pr_split/mmstar.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther88.9 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther99.9 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther79.7 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther91.6 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther96.7 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther87.9 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther88.7 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther95.2 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther93.2 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther104.6 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther87.8 KB
pr_split/mmstar.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther100.0 KB
pr_split/mmstar.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther67.3 KB
pr_split/mmstar.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther65.2 KB
pr_split/mmstar.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther71.1 KB
pr_split/mmvet.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther185.2 KB
pr_split/mmvet.claude_opus_4_8.llama4s17b.per_sample.jsonlOther222.0 KB
pr_split/mmvet.claude_opus_4_8.q35_9b.per_sample.jsonlOther185.0 KB
pr_split/mmvet.claude_opus_4_8.q3vl2b.per_sample.jsonlOther121.1 KB
pr_split/mmvet.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther151.7 KB
pr_split/mmvet.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther196.6 KB
pr_split/mmvet.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther261.1 KB
pr_split/mmvet.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther177.4 KB
pr_split/mmvet.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther144.7 KB
pr_split/mmvet.claude_opus_4_8.q3vl4b.per_sample.jsonlOther194.4 KB
pr_split/mmvet.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther227.1 KB
pr_split/mmvet.claude_opus_4_8.q3vl4b_vsr1_90.per_sample.jsonlOther198.9 KB
pr_split/mmvet.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther165.4 KB
pr_split/mmvet.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther201.2 KB
pr_split/mmvet.gpt_5_6_luna.q35_9b.per_sample.jsonlOther167.9 KB
pr_split/mmvet.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther108.0 KB
pr_split/mmvet.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther134.8 KB
pr_split/mmvet.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther177.0 KB
pr_split/mmvet.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther234.3 KB
pr_split/mmvet.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther161.8 KB
pr_split/mmvet.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther129.9 KB
pr_split/mmvet.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther175.6 KB
pr_split/mmvet.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther207.9 KB
pr_split/perceptionbench.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther207.7 KB
pr_split/perceptionbench.claude_opus_4_8.llama4s17b.per_sample.jsonlOther219.9 KB
pr_split/perceptionbench.claude_opus_4_8.q35_9b.per_sample.jsonlOther194.7 KB
pr_split/perceptionbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther231.0 KB
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther222.0 KB
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther215.3 KB
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther227.4 KB
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther217.0 KB
pr_split/perceptionbench.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther221.0 KB
pr_split/perceptionbench.claude_opus_4_8.q3vl4b.per_sample.jsonlOther213.4 KB
pr_split/perceptionbench.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther148.6 KB
pr_split/perceptionbench.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther162.0 KB
pr_split/perceptionbench.gpt_5_6_luna.q35_9b.per_sample.jsonlOther143.9 KB
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther174.1 KB
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther164.0 KB
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther164.8 KB
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther171.9 KB
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther162.2 KB
pr_split/perceptionbench.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther168.7 KB
pr_split/perceptionbench.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther159.9 KB
pr_split/realworldqa.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther95.2 KB
pr_split/realworldqa.claude_opus_4_8.llama4s17b.per_sample.jsonlOther66.4 KB
pr_split/realworldqa.claude_opus_4_8.q35_9b.per_sample.jsonlOther89.8 KB
pr_split/realworldqa.claude_opus_4_8.q3vl2b.per_sample.jsonlOther74.6 KB
pr_split/realworldqa.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther81.8 KB
pr_split/realworldqa.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther83.6 KB
pr_split/realworldqa.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther90.4 KB
pr_split/realworldqa.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther85.7 KB
pr_split/realworldqa.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther79.6 KB
pr_split/realworldqa.claude_opus_4_8.q3vl4b.per_sample.jsonlOther82.7 KB
pr_split/realworldqa.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther70.7 KB
pr_split/realworldqa.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther75.3 KB
pr_split/realworldqa.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther52.9 KB
pr_split/realworldqa.gpt_5_6_luna.q35_9b.per_sample.jsonlOther72.2 KB
pr_split/realworldqa.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther59.4 KB
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther63.8 KB
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther67.1 KB
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther72.3 KB
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther68.3 KB
pr_split/realworldqa.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther61.5 KB
pr_split/realworldqa.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther65.3 KB
pr_split/realworldqa.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther56.5 KB
pr_split/scienceqa.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther30.7 KB
pr_split/scienceqa.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther22.9 KB
pr_split/scienceqa.claude_opus_4_8.llama4s17b.per_sample.jsonlOther10.0 KB
pr_split/scienceqa.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther8.6 KB
pr_split/scienceqa.claude_opus_4_8.q35_9b.per_sample.jsonlOther31.3 KB
pr_split/scienceqa.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther35.7 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b.per_sample.jsonlOther41.2 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther28.1 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther41.8 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther22.1 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther27.3 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther35.1 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther28.0 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther27.4 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther48.2 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther21.2 KB
pr_split/scienceqa.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther28.0 KB
pr_split/scienceqa.claude_opus_4_8.q3vl4b.per_sample.jsonlOther13.6 KB
pr_split/scienceqa.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther17.4 KB
pr_split/scienceqa.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther23.5 KB
pr_split/scienceqa.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther16.8 KB
pr_split/scienceqa.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther7.9 KB
pr_split/scienceqa.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther5.9 KB
pr_split/scienceqa.gpt_5_6_luna.q35_9b.per_sample.jsonlOther23.9 KB
pr_split/scienceqa.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther29.3 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther32.3 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther21.9 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther35.9 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther17.3 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther22.0 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther29.4 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther21.8 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther21.3 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther38.8 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther18.0 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther21.5 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther11.1 KB
pr_split/scienceqa.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther14.1 KB
pr_split/visnumbench.claude_opus_4_8.gemma3_27b.per_sample.jsonlOther186.8 KB
pr_split/visnumbench.claude_opus_4_8.gemma3_27b_mc.per_sample.jsonlOther174.8 KB
pr_split/visnumbench.claude_opus_4_8.llama4s17b.per_sample.jsonlOther179.9 KB
pr_split/visnumbench.claude_opus_4_8.llama4s17b_mc.per_sample.jsonlOther176.9 KB
pr_split/visnumbench.claude_opus_4_8.q35_9b.per_sample.jsonlOther186.0 KB
pr_split/visnumbench.claude_opus_4_8.q35_9b_mc.per_sample.jsonlOther175.0 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b.per_sample.jsonlOther201.8 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_4bx3_270.per_sample.jsonlOther167.8 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_4bx3_270_mc.per_sample.jsonlOther170.6 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_4bx_270.per_sample.jsonlOther199.0 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_dapo270.per_sample.jsonlOther175.9 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_dapo270_mc.per_sample.jsonlOther165.8 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_grpo270.per_sample.jsonlOther192.6 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_grpo270_mc.per_sample.jsonlOther180.8 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_mc.per_sample.jsonlOther203.6 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_vsr1_270.per_sample.jsonlOther183.5 KB
pr_split/visnumbench.claude_opus_4_8.q3vl2b_vsr1_270_mc.per_sample.jsonlOther185.5 KB
pr_split/visnumbench.claude_opus_4_8.q3vl4b.per_sample.jsonlOther165.5 KB
pr_split/visnumbench.claude_opus_4_8.q3vl4b_grpo180.per_sample.jsonlOther167.2 KB
pr_split/visnumbench.claude_opus_4_8.q3vl4b_mc.per_sample.jsonlOther160.5 KB
pr_split/visnumbench.gpt_5_6_luna.gemma3_27b.per_sample.jsonlOther143.2 KB
pr_split/visnumbench.gpt_5_6_luna.gemma3_27b_mc.per_sample.jsonlOther136.0 KB
pr_split/visnumbench.gpt_5_6_luna.llama4s17b.per_sample.jsonlOther138.0 KB
pr_split/visnumbench.gpt_5_6_luna.llama4s17b_mc.per_sample.jsonlOther138.9 KB
pr_split/visnumbench.gpt_5_6_luna.q35_9b.per_sample.jsonlOther145.7 KB
pr_split/visnumbench.gpt_5_6_luna.q35_9b_mc.per_sample.jsonlOther139.4 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b.per_sample.jsonlOther154.5 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_4bx3_270.per_sample.jsonlOther130.0 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_4bx3_270_mc.per_sample.jsonlOther134.2 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_4bx_270.per_sample.jsonlOther152.9 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_dapo270.per_sample.jsonlOther137.2 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_dapo270_mc.per_sample.jsonlOther131.8 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_grpo270.per_sample.jsonlOther146.1 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_grpo270_mc.per_sample.jsonlOther139.0 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_mc.per_sample.jsonlOther158.5 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_vsr1_270.per_sample.jsonlOther141.1 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl2b_vsr1_270_mc.per_sample.jsonlOther146.6 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl4b.per_sample.jsonlOther124.9 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl4b_grpo180.per_sample.jsonlOther129.2 KB
pr_split/visnumbench.gpt_5_6_luna.q3vl4b_mc.per_sample.jsonlOther127.2 KB
samples/blink/img_0_0.pngOther4.3 MB 973d2abab42d
samples/blink/img_0_1.pngOther6.2 MB 9603cd1ff0dc
samples/blink/img_0_2.pngOther3.0 MB 40d029bb16ae
samples/blink/img_100_0.pngOther181.6 KB 319faa586a5c
samples/blink/img_101_0.pngOther250.6 KB fbbb83e8030d
samples/blink/img_102_0.pngOther58.8 KB
samples/blink/img_103_0.pngOther61.9 KB
samples/blink/img_104_0.pngOther72.2 KB
samples/blink/img_105_0.pngOther36.9 KB
samples/blink/img_106_0.pngOther72.8 KB
samples/blink/img_107_0.pngOther487.3 KB a5962e71f55c
samples/blink/img_108_0.pngOther565.1 KB c64197cccc26
samples/blink/img_109_0.pngOther443.3 KB f02539691b81
samples/blink/img_10_0.pngOther2.9 MB ecdd47a6c279
samples/blink/img_10_1.pngOther3.7 MB 4359a869645f
samples/blink/img_10_2.pngOther2.1 MB a6680fc51d37
samples/blink/img_110_0.pngOther371.7 KB 50244dc3a9c6
samples/blink/img_111_0.pngOther569.1 KB a648685fd54b
samples/blink/img_112_0.pngOther329.8 KB a8056d0987e1
samples/blink/img_113_0.pngOther232.5 KB f5c5efd029f8
samples/blink/img_114_0.pngOther270.6 KB c02bfce1a8e0
samples/blink/img_115_0.pngOther631.0 KB 25cb883b29d2
samples/blink/img_116_0.pngOther355.6 KB b21ed0f0be98
samples/blink/img_117_0.pngOther288.4 KB 1f4da00ae6df
samples/blink/img_118_0.pngOther531.9 KB 39ab02bba48d
samples/blink/img_119_0.pngOther287.0 KB 033ca69860d3
samples/blink/img_11_0.pngOther2.9 MB db523d74b57d
samples/blink/img_11_1.pngOther2.8 MB 9a0333ec73ef
samples/blink/img_11_2.pngOther3.4 MB 858099361fe7
samples/blink/img_120_0.pngOther435.0 KB 664b246bffe5
samples/blink/img_120_1.pngOther435.7 KB 3798aa575ec9
samples/blink/img_121_0.pngOther916.3 KB 422ddba50386
samples/blink/img_121_1.pngOther1.8 MB 60870dd7c540
samples/blink/img_122_0.pngOther865.1 KB 6dc16f74c631
samples/blink/img_122_1.pngOther2.6 MB f652264209e0
samples/blink/img_123_0.pngOther1.3 MB 190c7b52c0d8
samples/blink/img_123_1.pngOther2.0 MB 80eebb6dcd8a
samples/blink/img_124_0.pngOther2.3 MB 63ceb75c67f8
samples/blink/img_124_1.pngOther2.0 MB 89e161898c73
samples/blink/img_125_0.pngOther2.8 MB 0495f21ab3ab
samples/blink/img_125_1.pngOther1.9 MB cad67ac83f89
samples/blink/img_126_0.pngOther1.8 MB af168161e9e5
samples/blink/img_126_1.pngOther1.7 MB 89886d81d927
samples/blink/img_127_0.pngOther101.3 KB e75aa707fcf7
samples/blink/img_127_1.pngOther1.4 MB 5476b762c9de
samples/blink/img_128_0.pngOther979.8 KB ed450772023c
samples/blink/img_128_1.pngOther1.6 MB 4125523be7d7
samples/blink/img_129_0.pngOther1.4 MB e401b0a2022f
samples/blink/img_129_1.pngOther1.0 MB b2a5a983acc4
samples/blink/img_12_0.pngOther4.0 MB 896c6efa6ba1
samples/blink/img_12_1.pngOther3.2 MB d077c88cded1
samples/blink/img_12_2.pngOther5.0 MB b0380c9ab93e
samples/blink/img_130_0.pngOther1.2 MB 2f510b4517e4
samples/blink/img_130_1.pngOther1.6 MB 3adc7eed7fb4
samples/blink/img_131_0.pngOther1.8 MB 788182f31f50
samples/blink/img_131_1.pngOther1.5 MB b4a8083765d1
samples/blink/img_132_0.pngOther1.3 MB c0b226d003c9
samples/blink/img_132_1.pngOther1.4 MB a03ddda31a24
samples/blink/img_133_0.pngOther534.6 KB 102fdb3e89ce
samples/blink/img_133_1.pngOther1.6 MB a78187cedcd5
samples/blink/img_134_0.pngOther1.7 MB 47b903b07542
samples/blink/img_134_1.pngOther1.1 MB 50044fa534e4
samples/blink/img_135_0.pngOther1.6 MB 2e6684f07b2b
samples/blink/img_135_1.pngOther746.3 KB af2d10cc8a76
samples/blink/img_136_0.pngOther837.2 KB 53872be342c0
samples/blink/img_136_1.pngOther967.2 KB 899fa489f047
samples/blink/img_136_2.pngOther592.9 KB 1f55b048e4d2
samples/blink/img_137_0.pngOther807.5 KB 89e9a83cbfa9
samples/blink/img_137_1.pngOther699.6 KB 7906a08fc948
samples/blink/img_137_2.pngOther689.4 KB 4ffedb805feb
samples/blink/img_138_0.pngOther997.8 KB 5061e6bd415f
samples/blink/img_138_1.pngOther833.3 KB f6c3d946d56f
samples/blink/img_138_2.pngOther805.0 KB a109305d5eab
samples/blink/img_139_0.pngOther1.1 MB 881a53c2c3b2
samples/blink/img_139_1.pngOther591.1 KB 73a3b49ada2b
samples/blink/img_139_2.pngOther894.2 KB ef6adf66b4d1
samples/blink/img_13_0.pngOther310.3 KB d22680a80ea9
samples/blink/img_13_1.pngOther143.4 KB cdf8755cbc28
samples/blink/img_140_0.pngOther883.4 KB 32e6bcd7af3e
samples/blink/img_140_1.pngOther616.1 KB a48aa8aa1403
samples/blink/img_140_2.pngOther977.1 KB 8d0f55805bb8
samples/blink/img_141_0.pngOther878.3 KB 05a711561098
samples/blink/img_141_1.pngOther798.0 KB 969be3b9319c
samples/blink/img_141_2.pngOther938.5 KB 4da43c0271bc
samples/blink/img_142_0.pngOther223.3 KB 79fba4de8e0e
samples/blink/img_142_1.pngOther533.1 KB 9d82e33df098
samples/blink/img_142_2.pngOther619.8 KB 4f14118c05cf
samples/blink/img_143_0.pngOther812.3 KB 0756f8e111eb
samples/blink/img_143_1.pngOther543.5 KB b52584299625
samples/blink/img_143_2.pngOther571.4 KB edf3bb1f2f8b
samples/blink/img_144_0.pngOther999.8 KB fb630cd5889a
samples/blink/img_144_1.pngOther1.1 MB e179f78d2c80
samples/blink/img_144_2.pngOther1.1 MB 4794af5b65e0
samples/blink/img_145_0.pngOther781.3 KB 415b34d4c0d5
samples/blink/img_145_1.pngOther896.1 KB 710508f6ffbe
samples/blink/img_145_2.pngOther533.7 KB e59240650509
samples/blink/img_146_0.pngOther524.7 KB a2b8d5992533
samples/blink/img_146_1.pngOther372.7 KB 7b0d3aeb10ee
samples/blink/img_146_2.pngOther524.7 KB ecb6bc02db58
samples/blink/img_147_0.pngOther1.0 MB 9f37fb589872
samples/blink/img_147_1.pngOther1.3 MB 0022d73f4e49
samples/blink/img_147_2.pngOther1.0 MB b6a58cb19aab
samples/blink/img_148_0.pngOther924.6 KB cbdc6e452c02
samples/blink/img_148_1.pngOther559.1 KB 42d91ece86eb
samples/blink/img_148_2.pngOther710.3 KB bc1950a2d855
samples/blink/img_149_0.pngOther1.0 MB b2eec6040327
samples/blink/img_149_1.pngOther991.1 KB d58ffadce20b
samples/blink/img_149_2.pngOther1.1 MB d39950fbf584
samples/blink/img_14_0.pngOther1.1 MB 9f74520c321e
samples/blink/img_14_1.pngOther1.5 MB 2ea9c0875034
samples/blink/img_150_0.pngOther1.3 MB 805b335e6eac
samples/blink/img_150_1.pngOther1.2 MB c73f5dfcf4a3
samples/blink/img_150_2.pngOther1.1 MB e1729ad59379
samples/blink/img_151_0.pngOther311.8 KB 680684e3a192
samples/blink/img_151_1.pngOther326.9 KB 589c8fc75bb3
samples/blink/img_151_2.pngOther259.0 KB 3ca9d005b797
samples/blink/img_151_3.pngOther588.5 KB e7ec03bed7b4
samples/blink/img_152_0.pngOther270.4 KB ba8c3fa317ad
samples/blink/img_152_1.pngOther221.4 KB bcd69f9780f8
samples/blink/img_152_2.pngOther255.2 KB d6e729042ccf
samples/blink/img_152_3.pngOther207.1 KB 91e879532cd9
samples/blink/img_153_0.pngOther268.4 KB 852ad95a449c
samples/blink/img_153_1.pngOther250.3 KB f87f031bec98
samples/blink/img_153_2.pngOther332.2 KB 165ee746718a
samples/blink/img_153_3.pngOther260.6 KB 1952586c2f03
samples/blink/img_154_0.pngOther280.6 KB 0c43ad9c6e22
samples/blink/img_154_1.pngOther268.7 KB 33389691a510
samples/blink/img_154_2.pngOther273.4 KB 043b43512406
samples/blink/img_154_3.pngOther303.4 KB ef32bb236415
samples/blink/img_155_0.pngOther360.5 KB 8e91e6c44cd7
samples/blink/img_155_1.pngOther357.3 KB cdc351259fa9
samples/blink/img_155_2.pngOther337.9 KB 06ebee61b157
samples/blink/img_155_3.pngOther314.5 KB dd67d5d2ff92
samples/blink/img_156_0.pngOther382.4 KB 133f27a11fba
samples/blink/img_156_1.pngOther235.3 KB d277b9302272
samples/blink/img_156_2.pngOther268.5 KB 76b8116cbb91
samples/blink/img_156_3.pngOther260.9 KB 8258c982b722
samples/blink/img_157_0.pngOther318.4 KB 6f81cd9f57a5
samples/blink/img_157_1.pngOther395.6 KB c4be8d70b11b
samples/blink/img_157_2.pngOther349.1 KB 48a511ccdb4d
samples/blink/img_157_3.pngOther363.3 KB 8c3eb8a94bbe
samples/blink/img_158_0.pngOther303.7 KB 32e141cc4f43
samples/blink/img_158_1.pngOther256.1 KB f3670cb73042
samples/blink/img_158_2.pngOther261.4 KB ec38c38467d0
samples/blink/img_158_3.pngOther282.3 KB 894ca11c5bc2
samples/blink/img_159_0.pngOther325.4 KB 5586f9cfb8a2
samples/blink/img_159_1.pngOther241.8 KB 33ee19008d71
samples/blink/img_159_2.pngOther335.6 KB 7ac0d47f056d
samples/blink/img_159_3.pngOther306.4 KB 30ef89590fe3
samples/blink/img_15_0.pngOther347.0 KB e4fca349df82
samples/blink/img_15_1.pngOther114.7 KB c9c6936fb630
samples/blink/img_160_0.pngOther347.2 KB bb25cd82bfc4
samples/blink/img_160_1.pngOther294.6 KB 20706f32ee4f
samples/blink/img_160_2.pngOther339.3 KB 3da623ea6b51
samples/blink/img_160_3.pngOther316.8 KB e986bad526fd
samples/blink/img_161_0.pngOther407.9 KB 31a45020feec
samples/blink/img_161_1.pngOther302.6 KB 303f73d27ad9
samples/blink/img_161_2.pngOther332.6 KB 8f8e247846b4
samples/blink/img_161_3.pngOther339.7 KB 0b9020533cfb
samples/blink/img_162_0.pngOther365.5 KB 7ce605d93719
samples/blink/img_162_1.pngOther360.2 KB dbf54b2d894c
samples/blink/img_162_2.pngOther435.4 KB 2e146b121efe
samples/blink/img_162_3.pngOther394.5 KB 975e4ad57c5e
samples/blink/img_163_0.pngOther508.8 KB 382cbe6cf2ee
samples/blink/img_163_1.pngOther324.6 KB 50e61ab1af3a
samples/blink/img_163_2.pngOther356.7 KB c19e3d2dd5c5
samples/blink/img_163_3.pngOther337.5 KB 4ddcf89e0ef4
samples/blink/img_164_0.pngOther344.0 KB ea40080fbf09
samples/blink/img_164_1.pngOther348.5 KB d42934fcf237
samples/blink/img_164_2.pngOther365.4 KB 1cf0c787e19e
samples/blink/img_164_3.pngOther282.2 KB 172440ec4753
samples/blink/img_165_0.pngOther73.8 KB
samples/blink/img_165_1.pngOther23.6 KB
samples/blink/img_165_2.pngOther29.5 KB
samples/blink/img_166_0.pngOther55.0 KB
samples/blink/img_166_1.pngOther17.7 KB
samples/blink/img_166_2.pngOther33.7 KB
samples/blink/img_167_0.pngOther133.1 KB 9aaa5e8affac
samples/blink/img_167_1.pngOther42.8 KB
samples/blink/img_167_2.pngOther40.7 KB
samples/blink/img_168_0.pngOther81.6 KB
samples/blink/img_168_1.pngOther33.5 KB
samples/blink/img_168_2.pngOther25.5 KB
samples/blink/img_169_0.pngOther118.2 KB eaf3f05ef329
samples/blink/img_169_1.pngOther43.8 KB
samples/blink/img_169_2.pngOther29.2 KB
samples/blink/img_16_0.pngOther158.1 KB ffba1046d0b1
samples/blink/img_16_1.pngOther407.6 KB da6a590cc5d1
samples/blink/img_170_0.pngOther108.4 KB 31a30e294f7c
samples/blink/img_170_1.pngOther38.8 KB
samples/blink/img_170_2.pngOther27.5 KB
samples/blink/img_171_0.pngOther118.3 KB 5f9729625c64
samples/blink/img_171_1.pngOther43.4 KB
samples/blink/img_171_2.pngOther49.8 KB
samples/blink/img_172_0.pngOther63.5 KB
samples/blink/img_172_1.pngOther23.5 KB
samples/blink/img_172_2.pngOther14.7 KB
samples/blink/img_173_0.pngOther126.7 KB a1490371b698
samples/blink/img_173_1.pngOther44.6 KB
samples/blink/img_173_2.pngOther42.1 KB
samples/blink/img_174_0.pngOther88.9 KB
samples/blink/img_174_1.pngOther31.5 KB
samples/blink/img_174_2.pngOther32.5 KB
samples/blink/img_175_0.pngOther97.1 KB
samples/blink/img_175_1.pngOther25.6 KB
samples/blink/img_175_2.pngOther33.8 KB
samples/blink/img_176_0.pngOther96.9 KB
samples/blink/img_176_1.pngOther41.5 KB
samples/blink/img_176_2.pngOther39.1 KB
samples/blink/img_177_0.pngOther125.0 KB 73a1dca1766e
samples/blink/img_177_1.pngOther41.5 KB
samples/blink/img_177_2.pngOther27.2 KB
samples/blink/img_178_0.pngOther21.2 KB
samples/blink/img_178_1.pngOther10.2 KB
samples/blink/img_178_2.pngOther20.2 KB
samples/blink/img_179_0.pngOther136.2 KB 905ea83ab928
samples/blink/img_179_1.pngOther30.2 KB
samples/blink/img_179_2.pngOther46.4 KB
samples/blink/img_17_0.pngOther390.8 KB 851f8f7e21d8
samples/blink/img_17_1.pngOther1.7 MB 3509ad6e8e09
samples/blink/img_180_0.pngOther94.1 KB
samples/blink/img_180_1.pngOther43.1 KB
samples/blink/img_180_2.pngOther41.6 KB
samples/blink/img_181_0.pngOther75.6 KB
samples/blink/img_181_1.pngOther36.7 KB
samples/blink/img_181_2.pngOther18.0 KB
samples/blink/img_182_0.pngOther226.2 KB 23a4864beac6
samples/blink/img_183_0.pngOther303.9 KB fbec9372ef7a
samples/blink/img_184_0.pngOther196.7 KB b090716be8ef
samples/blink/img_185_0.pngOther398.8 KB 7ef8d7488e07
samples/blink/img_186_0.pngOther248.6 KB e9fea7ffa3f2
samples/blink/img_187_0.pngOther199.0 KB 704178a43b16
samples/blink/img_188_0.pngOther194.2 KB 34f2b6be73da
samples/blink/img_189_0.pngOther248.6 KB a0d7eb285ddb
samples/blink/img_18_0.pngOther217.1 KB c2d7481955af
samples/blink/img_18_1.pngOther556.4 KB 85e58449ba74
samples/blink/img_190_0.pngOther303.9 KB 11bd522cdf4a
samples/blink/img_191_0.pngOther285.5 KB 6bfbd0b779a9
samples/blink/img_192_0.pngOther189.9 KB 8e26856b4cd4
samples/blink/img_193_0.pngOther266.2 KB b319fb734850
samples/blink/img_194_0.pngOther220.1 KB e11c49ce1e8b
samples/blink/img_195_0.pngOther309.4 KB 2597a8754819
samples/blink/img_196_0.pngOther234.4 KB d831895af942
samples/blink/img_197_0.pngOther407.3 KB e91b98779ce6
samples/blink/img_198_0.pngOther797.4 KB 2c2e0a6e1b41
samples/blink/img_199_0.pngOther509.1 KB 6c682efeb33c
samples/blink/img_19_0.pngOther1.1 MB 13d7fee9856f
samples/blink/img_19_1.pngOther651.0 KB 8fc1c02dc2c4
samples/blink/img_1_0.pngOther3.2 MB a1b3c3c4c8c7
samples/blink/img_1_1.pngOther5.0 MB cbecbd487802
samples/blink/img_1_2.pngOther2.9 MB 64b5700ac036
samples/blink/img_20_0.pngOther679.5 KB 76e4db95f5f3
samples/blink/img_20_1.pngOther196.2 KB fd07cc9f23af
samples/blink/img_21_0.pngOther586.5 KB de0f1ef943f2
samples/blink/img_21_1.pngOther465.6 KB 6a0c771bb7d0
samples/blink/img_22_0.pngOther130.3 KB 4dd2c6bdbc6b
samples/blink/img_22_1.pngOther497.6 KB 44d62264b06c
samples/blink/img_23_0.pngOther1.2 MB e573403e71f1
samples/blink/img_23_1.pngOther844.3 KB f944951370bd
samples/blink/img_24_0.pngOther1.6 MB c99e55f4f193
samples/blink/img_24_1.pngOther1.3 MB 810d9b406682
samples/blink/img_25_0.pngOther72.5 KB
samples/blink/img_25_1.pngOther889.5 KB c0cd443ab244
samples/blink/img_26_0.pngOther1.3 MB 214fab72d9a8
samples/blink/img_26_1.pngOther1.4 MB f57a33a50979
samples/blink/img_27_0.pngOther655.6 KB 6303c8e4593f
samples/blink/img_27_1.pngOther542.2 KB 1b1cda76eb92
samples/blink/img_28_0.pngOther233.7 KB eb033c5037de
samples/blink/img_28_1.pngOther284.1 KB 9fa46202000a
samples/blink/img_29_0.pngOther204.9 KB 0b36bad4eb57
samples/blink/img_29_1.pngOther231.0 KB b5bf56337297
samples/blink/img_2_0.pngOther3.9 MB c5cc14206986
samples/blink/img_2_1.pngOther2.0 MB 7a3919413a6f
samples/blink/img_2_2.pngOther2.3 MB 2178930c2f77
samples/blink/img_30_0.pngOther404.0 KB e0231fa0d70d
samples/blink/img_30_1.pngOther391.8 KB 7b4651a6e0e4
samples/blink/img_31_0.pngOther171.3 KB 93a5ace7ea91
samples/blink/img_31_1.pngOther177.3 KB 28f67a9c2e3e
samples/blink/img_32_0.pngOther235.1 KB ad5f433ce8ed
samples/blink/img_32_1.pngOther205.1 KB d2ef20a6c145
samples/blink/img_33_0.pngOther433.7 KB 63d760609544
samples/blink/img_33_1.pngOther390.5 KB 2f71b60f48e2
samples/blink/img_34_0.pngOther369.4 KB 403e5904ee65
samples/blink/img_34_1.pngOther320.2 KB 89ff4fe78c23
samples/blink/img_35_0.pngOther395.4 KB ced143f12bb5
samples/blink/img_35_1.pngOther343.9 KB 21cf0819ece1
samples/blink/img_36_0.pngOther216.0 KB b3353bd7c04a
samples/blink/img_36_1.pngOther376.3 KB 66be7d3c712f
samples/blink/img_37_0.pngOther425.0 KB f696316fec6d
samples/blink/img_37_1.pngOther396.0 KB 48e295d7ce10
samples/blink/img_38_0.pngOther530.6 KB f05ac0bedf0d
samples/blink/img_38_1.pngOther506.4 KB f5a864a33282
samples/blink/img_39_0.pngOther167.7 KB ae76c278ff28
samples/blink/img_39_1.pngOther149.8 KB 2e717661a5b7
samples/blink/img_3_0.pngOther2.1 MB 0f2727def51e
samples/blink/img_3_1.pngOther2.2 MB 5c0fcc593298
samples/blink/img_3_2.pngOther2.1 MB d14c132d8dc3
samples/blink/img_40_0.pngOther346.5 KB f2e57ce9ef87
samples/blink/img_40_1.pngOther327.6 KB 9e69bad8e024
samples/blink/img_41_0.pngOther374.2 KB a0ea9a6baddd
samples/blink/img_41_1.pngOther458.2 KB 722bca4bb8f1
samples/blink/img_42_0.pngOther187.5 KB c33d0fd67e8d
samples/blink/img_42_1.pngOther123.7 KB 21794acf8b7e
samples/blink/img_43_0.pngOther1.8 MB 5e39c984ae7a
samples/blink/img_44_0.pngOther508.5 KB 837baf18fb53
samples/blink/img_45_0.pngOther717.2 KB 1ba8b24d3729
samples/blink/img_46_0.pngOther931.8 KB 4fb7ced2d067
samples/blink/img_47_0.pngOther1.3 MB 2dda1a68dd7a
samples/blink/img_48_0.pngOther575.7 KB cb8e88c13be0
samples/blink/img_49_0.pngOther965.7 KB 737d76ff55ee
samples/blink/img_4_0.pngOther1.3 MB 701a2938fec7
samples/blink/img_4_1.pngOther2.6 MB 52b44ef75534
samples/blink/img_4_2.pngOther2.1 MB 427ec2ece1c5
samples/blink/img_50_0.pngOther1.0 MB 73d1cad0a0fd
samples/blink/img_51_0.pngOther1.2 MB bc6b507f4c60
samples/blink/img_52_0.pngOther2.2 MB 76c9b4b6df48
samples/blink/img_53_0.pngOther1.6 MB 52087166283b
samples/blink/img_54_0.pngOther1.6 MB e1a6d6ebded7
samples/blink/img_55_0.pngOther1.0 MB b650790d3f94
samples/blink/img_56_0.pngOther621.6 KB dac88144e3eb
samples/blink/img_57_0.pngOther1.5 MB 64bb677e15b0
samples/blink/img_58_0.pngOther1.6 MB 83745dd88cd0
samples/blink/img_58_1.pngOther2.1 MB bb1e216af6e2
samples/blink/img_59_0.pngOther2.1 MB 44514f6e65bd
samples/blink/img_59_1.pngOther2.1 MB 656bb83a7321
samples/blink/img_5_0.pngOther2.0 MB 0dfd3f80ef7c
samples/blink/img_5_1.pngOther4.1 MB 3dbc0db08850
samples/blink/img_5_2.pngOther4.0 MB 0dc44deb03e9
samples/blink/img_60_0.pngOther2.0 MB dc658ab90d8a
samples/blink/img_60_1.pngOther2.4 MB 7f5b1e15bdcf
samples/blink/img_61_0.pngOther1.0 MB ba0a97b5b1c0
samples/blink/img_61_1.pngOther1.2 MB c9bf3bde3714
samples/blink/img_62_0.pngOther1.8 MB b7d781e5c4f4
samples/blink/img_62_1.pngOther1.6 MB 7a7c491402be
samples/blink/img_63_0.pngOther327.1 KB f6a9ecd60f93
samples/blink/img_63_1.pngOther496.5 KB 66309aa626ad
samples/blink/img_64_0.pngOther1.5 MB ac0742b2823b
samples/blink/img_64_1.pngOther1.7 MB 074704c32f51
samples/blink/img_65_0.pngOther1.6 MB e78e6f77d740
samples/blink/img_65_1.pngOther1.6 MB fff62646ee2f
samples/blink/img_66_0.pngOther954.2 KB 0c9bee3ba588
samples/blink/img_66_1.pngOther950.5 KB 934aa6ae3248
samples/blink/img_67_0.pngOther2.6 MB 8b2b5458da6a
samples/blink/img_67_1.pngOther2.7 MB ca7c5ea81127
samples/blink/img_68_0.pngOther1.8 MB 3e9c00791f63
samples/blink/img_68_1.pngOther1.9 MB 00253b2a8a70
samples/blink/img_69_0.pngOther2.3 MB 1020937ea191
samples/blink/img_69_1.pngOther2.5 MB 64d9a84bf893
samples/blink/img_6_0.pngOther3.2 MB 90084a8d10cf
samples/blink/img_6_1.pngOther2.4 MB 0fa3cacc264e
samples/blink/img_6_2.pngOther5.0 MB a808df607554
samples/blink/img_70_0.pngOther570.9 KB 0091360c2914
samples/blink/img_70_1.pngOther703.2 KB 5ae685ec5625
samples/blink/img_71_0.pngOther619.9 KB 775c32874ddc
samples/blink/img_71_1.pngOther761.8 KB ce7b877bea5c
samples/blink/img_72_0.pngOther1.8 MB 615e150fc741
samples/blink/img_72_1.pngOther1.6 MB 230690e226e9
samples/blink/img_73_0.pngOther1.1 MB 3790df7437bf
samples/blink/img_73_1.pngOther1.1 MB 31acafb06b90
samples/blink/img_74_0.pngOther1.5 MB 92fbd08e14e6
samples/blink/img_74_1.pngOther1.5 MB e2bdc9d28fe6
samples/blink/img_75_0.pngOther670.6 KB e1e7a4b8e0a4
samples/blink/img_75_1.pngOther581.9 KB b5930765d40f
samples/blink/img_76_0.pngOther1.8 MB f8653bb19488
samples/blink/img_76_1.pngOther1.3 MB 1de5271438b2
samples/blink/img_77_0.pngOther229.9 KB 715f9d9bf052
samples/blink/img_78_0.pngOther303.8 KB 4c987d358b01
samples/blink/img_79_0.pngOther241.9 KB 7b0a2cb72593
samples/blink/img_7_0.pngOther3.0 MB 76b220ba7ffc
samples/blink/img_7_1.pngOther3.3 MB 0bd36f56c5f4
samples/blink/img_7_2.pngOther5.3 MB e5b6e5eb2103
samples/blink/img_80_0.pngOther255.0 KB e89d9a44a5d4
samples/blink/img_81_0.pngOther209.2 KB d35668ba498b
samples/blink/img_82_0.pngOther249.8 KB ba387d7b7efd
samples/blink/img_83_0.pngOther384.4 KB 5b7e2896272e
samples/blink/img_84_0.pngOther224.2 KB 6d18333be32c
samples/blink/img_85_0.pngOther328.2 KB a0944950e39c
samples/blink/img_86_0.pngOther268.0 KB 4fe21bcf127f
samples/blink/img_87_0.pngOther242.1 KB 83d0048c5ce1
samples/blink/img_88_0.pngOther309.9 KB c38cb98911b7
samples/blink/img_89_0.pngOther334.4 KB edc29b2cc287
samples/blink/img_8_0.pngOther2.6 MB 4d99d860ed5f
samples/blink/img_8_1.pngOther3.0 MB 325ac4f584f6
samples/blink/img_8_2.pngOther4.1 MB b504c6ef95bc
samples/blink/img_90_0.pngOther35.3 KB
samples/blink/img_91_0.pngOther23.0 KB
samples/blink/img_92_0.pngOther20.8 KB
samples/blink/img_93_0.pngOther21.5 KB
samples/blink/img_94_0.pngOther34.3 KB
samples/blink/img_95_0.pngOther84.1 KB
samples/blink/img_96_0.pngOther67.0 KB
samples/blink/img_97_0.pngOther262.4 KB 52abca67840d
samples/blink/img_98_0.pngOther36.7 KB
samples/blink/img_99_0.pngOther18.3 KB
samples/blink/img_9_0.pngOther1.7 MB 32d3bd67ce11
samples/blink/img_9_1.pngOther3.1 MB 5114d88ec6a4
samples/blink/img_9_2.pngOther1.9 MB 2e0264d67531
samples/blink/meta.jsonlOther397.2 KB
samples/chartqa/img_0_0.pngOther41.0 KB
samples/chartqa/img_100_0.pngOther32.8 KB
samples/chartqa/img_101_0.pngOther33.0 KB
samples/chartqa/img_102_0.pngOther39.6 KB
samples/chartqa/img_103_0.pngOther35.5 KB
samples/chartqa/img_104_0.pngOther33.4 KB
samples/chartqa/img_105_0.pngOther33.6 KB
samples/chartqa/img_106_0.pngOther32.1 KB
samples/chartqa/img_107_0.pngOther44.1 KB
samples/chartqa/img_108_0.pngOther42.4 KB
samples/chartqa/img_109_0.pngOther27.5 KB
samples/chartqa/img_10_0.pngOther14.7 KB
samples/chartqa/img_110_0.pngOther43.4 KB
samples/chartqa/img_111_0.pngOther31.9 KB
samples/chartqa/img_112_0.pngOther41.8 KB
samples/chartqa/img_113_0.pngOther46.9 KB
samples/chartqa/img_114_0.pngOther35.2 KB
samples/chartqa/img_115_0.pngOther42.9 KB
samples/chartqa/img_116_0.pngOther57.1 KB
samples/chartqa/img_117_0.pngOther52.5 KB
samples/chartqa/img_118_0.pngOther52.1 KB
samples/chartqa/img_119_0.pngOther58.1 KB
samples/chartqa/img_11_0.pngOther71.9 KB
samples/chartqa/img_120_0.pngOther27.6 KB
samples/chartqa/img_121_0.pngOther55.5 KB
samples/chartqa/img_122_0.pngOther30.9 KB
samples/chartqa/img_123_0.pngOther28.5 KB
samples/chartqa/img_124_0.pngOther66.6 KB
samples/chartqa/img_125_0.pngOther32.5 KB
samples/chartqa/img_126_0.pngOther35.3 KB
samples/chartqa/img_127_0.pngOther39.8 KB
samples/chartqa/img_128_0.pngOther51.5 KB
samples/chartqa/img_129_0.pngOther29.2 KB
samples/chartqa/img_12_0.pngOther17.0 KB
samples/chartqa/img_130_0.pngOther44.9 KB
samples/chartqa/img_131_0.pngOther57.9 KB
samples/chartqa/img_132_0.pngOther39.2 KB
samples/chartqa/img_133_0.pngOther34.2 KB
samples/chartqa/img_134_0.pngOther33.7 KB
samples/chartqa/img_135_0.pngOther32.6 KB
samples/chartqa/img_136_0.pngOther32.6 KB
samples/chartqa/img_137_0.pngOther31.6 KB
samples/chartqa/img_138_0.pngOther40.2 KB
samples/chartqa/img_139_0.pngOther29.8 KB
samples/chartqa/img_13_0.pngOther19.5 KB
samples/chartqa/img_140_0.pngOther32.5 KB
samples/chartqa/img_141_0.pngOther41.5 KB
samples/chartqa/img_142_0.pngOther58.8 KB
samples/chartqa/img_143_0.pngOther45.6 KB
samples/chartqa/img_144_0.pngOther34.6 KB
samples/chartqa/img_145_0.pngOther28.8 KB
samples/chartqa/img_146_0.pngOther34.1 KB
samples/chartqa/img_147_0.pngOther37.5 KB
samples/chartqa/img_148_0.pngOther28.9 KB
samples/chartqa/img_149_0.pngOther37.1 KB
samples/chartqa/img_14_0.pngOther16.3 KB
samples/chartqa/img_150_0.pngOther48.0 KB
samples/chartqa/img_151_0.pngOther41.5 KB
samples/chartqa/img_152_0.pngOther35.4 KB
samples/chartqa/img_153_0.pngOther76.8 KB
samples/chartqa/img_154_0.pngOther25.7 KB
samples/chartqa/img_155_0.pngOther41.4 KB
samples/chartqa/img_156_0.pngOther28.5 KB
samples/chartqa/img_157_0.pngOther66.7 KB
samples/chartqa/img_158_0.pngOther40.4 KB
samples/chartqa/img_159_0.pngOther109.4 KB 2d6bf653bcfc
samples/chartqa/img_15_0.pngOther18.8 KB
samples/chartqa/img_160_0.pngOther63.5 KB
samples/chartqa/img_161_0.pngOther31.2 KB
samples/chartqa/img_162_0.pngOther28.3 KB
samples/chartqa/img_163_0.pngOther58.2 KB
samples/chartqa/img_164_0.pngOther34.2 KB
samples/chartqa/img_165_0.pngOther41.9 KB
samples/chartqa/img_166_0.pngOther31.9 KB
samples/chartqa/img_167_0.pngOther58.0 KB
samples/chartqa/img_168_0.pngOther30.7 KB
samples/chartqa/img_169_0.pngOther33.5 KB
samples/chartqa/img_16_0.pngOther20.3 KB
samples/chartqa/img_170_0.pngOther30.7 KB
samples/chartqa/img_171_0.pngOther46.9 KB
samples/chartqa/img_172_0.pngOther29.1 KB
samples/chartqa/img_173_0.pngOther33.2 KB
samples/chartqa/img_174_0.pngOther64.6 KB
samples/chartqa/img_175_0.pngOther39.2 KB
samples/chartqa/img_176_0.pngOther29.2 KB
samples/chartqa/img_177_0.pngOther43.7 KB
samples/chartqa/img_178_0.pngOther54.6 KB
samples/chartqa/img_179_0.pngOther30.6 KB
samples/chartqa/img_17_0.pngOther40.7 KB
samples/chartqa/img_180_0.pngOther64.1 KB
samples/chartqa/img_181_0.pngOther26.1 KB
samples/chartqa/img_182_0.pngOther27.4 KB
samples/chartqa/img_183_0.pngOther33.1 KB
samples/chartqa/img_184_0.pngOther30.4 KB
samples/chartqa/img_185_0.pngOther38.2 KB
samples/chartqa/img_186_0.pngOther38.0 KB
samples/chartqa/img_187_0.pngOther40.3 KB
samples/chartqa/img_188_0.pngOther29.8 KB
samples/chartqa/img_189_0.pngOther48.2 KB
samples/chartqa/img_18_0.pngOther23.3 KB
samples/chartqa/img_190_0.pngOther31.4 KB
samples/chartqa/img_191_0.pngOther29.7 KB
samples/chartqa/img_192_0.pngOther29.5 KB
samples/chartqa/img_193_0.pngOther55.5 KB
samples/chartqa/img_194_0.pngOther33.2 KB
samples/chartqa/img_195_0.pngOther60.7 KB
samples/chartqa/img_196_0.pngOther33.4 KB
samples/chartqa/img_197_0.pngOther38.1 KB
samples/chartqa/img_198_0.pngOther31.2 KB
samples/chartqa/img_199_0.pngOther72.8 KB
samples/chartqa/img_19_0.pngOther23.3 KB
samples/chartqa/img_1_0.pngOther36.6 KB
samples/chartqa/img_20_0.pngOther26.3 KB
samples/chartqa/img_21_0.pngOther42.8 KB
samples/chartqa/img_22_0.pngOther36.5 KB
samples/chartqa/img_23_0.pngOther39.4 KB
samples/chartqa/img_24_0.pngOther32.5 KB
samples/chartqa/img_25_0.pngOther31.7 KB
samples/chartqa/img_26_0.pngOther25.4 KB
samples/chartqa/img_27_0.pngOther44.8 KB
samples/chartqa/img_28_0.pngOther34.5 KB
samples/chartqa/img_29_0.pngOther37.1 KB
samples/chartqa/img_2_0.pngOther25.5 KB
samples/chartqa/img_30_0.pngOther18.6 KB
samples/chartqa/img_31_0.pngOther36.4 KB
samples/chartqa/img_32_0.pngOther41.2 KB
samples/chartqa/img_33_0.pngOther35.3 KB
samples/chartqa/img_34_0.pngOther26.1 KB
samples/chartqa/img_35_0.pngOther29.5 KB
samples/chartqa/img_36_0.pngOther25.7 KB
samples/chartqa/img_37_0.pngOther34.1 KB
samples/chartqa/img_38_0.pngOther122.8 KB 1c46112d2d80
samples/chartqa/img_39_0.pngOther23.1 KB
samples/chartqa/img_3_0.pngOther71.6 KB
samples/chartqa/img_40_0.pngOther23.7 KB
samples/chartqa/img_41_0.pngOther14.9 KB
samples/chartqa/img_42_0.pngOther18.4 KB
samples/chartqa/img_43_0.pngOther17.7 KB
samples/chartqa/img_44_0.pngOther11.6 KB
samples/chartqa/img_45_0.pngOther15.0 KB
samples/chartqa/img_46_0.pngOther13.8 KB
samples/chartqa/img_47_0.pngOther24.1 KB
samples/chartqa/img_48_0.pngOther34.3 KB
samples/chartqa/img_49_0.pngOther20.6 KB
samples/chartqa/img_4_0.pngOther16.0 KB
samples/chartqa/img_50_0.pngOther44.0 KB
samples/chartqa/img_51_0.pngOther29.1 KB
samples/chartqa/img_52_0.pngOther51.0 KB
samples/chartqa/img_53_0.pngOther27.1 KB
samples/chartqa/img_54_0.pngOther54.2 KB
samples/chartqa/img_55_0.pngOther27.7 KB
samples/chartqa/img_56_0.pngOther39.7 KB
samples/chartqa/img_57_0.pngOther36.5 KB
samples/chartqa/img_58_0.pngOther34.2 KB
samples/chartqa/img_59_0.pngOther43.4 KB
samples/chartqa/img_5_0.pngOther17.1 KB
samples/chartqa/img_60_0.pngOther40.2 KB
samples/chartqa/img_61_0.pngOther40.8 KB
samples/chartqa/img_62_0.pngOther54.5 KB
samples/chartqa/img_63_0.pngOther31.1 KB
samples/chartqa/img_64_0.pngOther39.9 KB
samples/chartqa/img_65_0.pngOther42.6 KB
samples/chartqa/img_66_0.pngOther30.9 KB
samples/chartqa/img_67_0.pngOther37.0 KB
samples/chartqa/img_68_0.pngOther48.4 KB
samples/chartqa/img_69_0.pngOther38.5 KB
samples/chartqa/img_6_0.pngOther107.2 KB 0819f6a8854f
samples/chartqa/img_70_0.pngOther54.9 KB
samples/chartqa/img_71_0.pngOther73.4 KB
samples/chartqa/img_72_0.pngOther46.0 KB
samples/chartqa/img_73_0.pngOther51.2 KB
samples/chartqa/img_74_0.pngOther69.9 KB
samples/chartqa/img_75_0.pngOther62.5 KB
samples/chartqa/img_76_0.pngOther39.8 KB
samples/chartqa/img_77_0.pngOther31.4 KB
samples/chartqa/img_78_0.pngOther55.8 KB
samples/chartqa/img_79_0.pngOther33.4 KB
samples/chartqa/img_7_0.pngOther34.9 KB
samples/chartqa/img_80_0.pngOther33.9 KB
samples/chartqa/img_81_0.pngOther59.6 KB
samples/chartqa/img_82_0.pngOther33.7 KB
samples/chartqa/img_83_0.pngOther30.6 KB
samples/chartqa/img_84_0.pngOther33.3 KB
samples/chartqa/img_85_0.pngOther34.9 KB
samples/chartqa/img_86_0.pngOther57.2 KB
samples/chartqa/img_87_0.pngOther36.6 KB
samples/chartqa/img_88_0.pngOther36.1 KB
samples/chartqa/img_89_0.pngOther33.6 KB
samples/chartqa/img_8_0.pngOther22.7 KB
samples/chartqa/img_90_0.pngOther54.5 KB
samples/chartqa/img_91_0.pngOther60.6 KB
samples/chartqa/img_92_0.pngOther29.1 KB
samples/chartqa/img_93_0.pngOther34.1 KB
samples/chartqa/img_94_0.pngOther33.1 KB
samples/chartqa/img_95_0.pngOther47.0 KB
samples/chartqa/img_96_0.pngOther36.4 KB
samples/chartqa/img_97_0.pngOther36.5 KB
samples/chartqa/img_98_0.pngOther30.9 KB
samples/chartqa/img_99_0.pngOther38.8 KB
samples/chartqa/img_9_0.pngOther25.2 KB
samples/chartqa/meta.jsonlOther232.2 KB
samples/hallusionbench/img_0_0.pngOther249.9 KB 94b55a84b7a7
samples/hallusionbench/img_100_0.pngOther12.9 KB
samples/hallusionbench/img_101_0.pngOther226.6 KB f364f47c1753
samples/hallusionbench/img_102_0.pngOther38.3 KB
samples/hallusionbench/img_103_0.pngOther18.6 KB
samples/hallusionbench/img_104_0.pngOther18.3 KB
samples/hallusionbench/img_105_0.pngOther16.9 KB
samples/hallusionbench/img_106_0.pngOther21.1 KB
samples/hallusionbench/img_107_0.pngOther28.9 KB
samples/hallusionbench/img_108_0.pngOther8.4 KB
samples/hallusionbench/img_109_0.pngOther5.0 KB
samples/hallusionbench/img_10_0.pngOther204.5 KB f89c907b7948
samples/hallusionbench/img_110_0.pngOther485.1 KB eb9da232d0f3
samples/hallusionbench/img_111_0.pngOther543.9 KB a2ca7e3a3a21
samples/hallusionbench/img_112_0.pngOther17.4 KB
samples/hallusionbench/img_113_0.pngOther17.3 KB
samples/hallusionbench/img_114_0.pngOther12.9 KB
samples/hallusionbench/img_115_0.pngOther12.7 KB
samples/hallusionbench/img_116_0.pngOther7.8 KB
samples/hallusionbench/img_117_0.pngOther70.4 KB
samples/hallusionbench/img_118_0.pngOther142.2 KB 44f9153c1931
samples/hallusionbench/img_119_0.pngOther19.9 KB
samples/hallusionbench/img_11_0.pngOther46.4 KB
samples/hallusionbench/img_120_0.pngOther20.4 KB
samples/hallusionbench/img_121_0.pngOther13.5 KB
samples/hallusionbench/img_122_0.pngOther12.8 KB
samples/hallusionbench/img_123_0.pngOther13.1 KB
samples/hallusionbench/img_124_0.pngOther4.6 KB
samples/hallusionbench/img_125_0.pngOther30.8 KB
samples/hallusionbench/img_126_0.pngOther67.3 KB
samples/hallusionbench/img_127_0.pngOther75.8 KB
samples/hallusionbench/img_128_0.pngOther42.7 KB
samples/hallusionbench/img_129_0.pngOther72.6 KB
samples/hallusionbench/img_12_0.pngOther243.5 KB 6ea8f1e6d45d
samples/hallusionbench/img_130_0.pngOther57.3 KB
samples/hallusionbench/img_131_0.pngOther66.9 KB
samples/hallusionbench/img_132_0.pngOther5.4 KB
samples/hallusionbench/img_133_0.pngOther5.9 KB
samples/hallusionbench/img_134_0.pngOther39.4 KB
samples/hallusionbench/img_135_0.pngOther163.1 KB d1aaac3fed02
samples/hallusionbench/img_136_0.pngOther177.2 KB c932201495bb
samples/hallusionbench/img_137_0.pngOther44.0 KB
samples/hallusionbench/img_138_0.pngOther13.0 KB
samples/hallusionbench/img_139_0.pngOther42.0 KB
samples/hallusionbench/img_13_0.pngOther198.2 KB d8dddfa80159
samples/hallusionbench/img_140_0.pngOther29.9 KB
samples/hallusionbench/img_141_0.pngOther61.6 KB
samples/hallusionbench/img_142_0.pngOther62.1 KB
samples/hallusionbench/img_143_0.pngOther61.9 KB
samples/hallusionbench/img_144_0.pngOther67.0 KB
samples/hallusionbench/img_145_0.pngOther67.7 KB
samples/hallusionbench/img_146_0.pngOther35.9 KB
samples/hallusionbench/img_147_0.pngOther61.3 KB
samples/hallusionbench/img_148_0.pngOther55.4 KB
samples/hallusionbench/img_149_0.pngOther36.5 KB
samples/hallusionbench/img_14_0.pngOther198.4 KB 9d0608f7c27d
samples/hallusionbench/img_150_0.pngOther36.2 KB
samples/hallusionbench/img_151_0.pngOther26.9 KB
samples/hallusionbench/img_152_0.pngOther64.0 KB
samples/hallusionbench/img_153_0.pngOther647.0 KB d0ba5c2e3d5e
samples/hallusionbench/img_154_0.pngOther371.2 KB 57bee4b5e7fb
samples/hallusionbench/img_155_0.pngOther2.8 MB 2a6ca9cd057f
samples/hallusionbench/img_156_0.pngOther409.1 KB d04dabd6de5a
samples/hallusionbench/img_157_0.pngOther638.3 KB 2ee2a2be61cb
samples/hallusionbench/img_158_0.pngOther638.5 KB 6220e3646e4f
samples/hallusionbench/img_159_0.pngOther118.2 KB e978b42ee02c
samples/hallusionbench/img_15_0.pngOther50.2 KB
samples/hallusionbench/img_160_0.pngOther220.0 KB 0a1f32dfc9c3
samples/hallusionbench/img_161_0.pngOther396.5 KB 10d9a8769ee7
samples/hallusionbench/img_162_0.pngOther30.9 KB
samples/hallusionbench/img_163_0.pngOther232.1 KB 6d01eb8f5446
samples/hallusionbench/img_164_0.pngOther507.4 KB b992881fa22e
samples/hallusionbench/img_165_0.pngOther739.7 KB ce643f5e8929
samples/hallusionbench/img_166_0.pngOther1.0 MB 70bc5542981a
samples/hallusionbench/img_167_0.pngOther365.0 KB 696d9d280a7d
samples/hallusionbench/img_168_0.pngOther135.3 KB 7926340294b2
samples/hallusionbench/img_169_0.pngOther456.4 KB 652806c447cf
samples/hallusionbench/img_16_0.pngOther50.0 KB
samples/hallusionbench/img_170_0.pngOther68.6 KB
samples/hallusionbench/img_171_0.pngOther137.1 KB 3bd5fb9dff41
samples/hallusionbench/img_172_0.pngOther418.3 KB dc69b37d9d99
samples/hallusionbench/img_173_0.pngOther359.5 KB b5a2c25427e0
samples/hallusionbench/img_174_0.pngOther213.4 KB 7059bece1083
samples/hallusionbench/img_175_0.pngOther328.9 KB 915d0b966207
samples/hallusionbench/img_176_0.pngOther46.4 KB
samples/hallusionbench/img_177_0.pngOther1.7 MB fa5a1e0b2d15
samples/hallusionbench/img_178_0.pngOther141.5 KB 9b44c41444bc
samples/hallusionbench/img_179_0.pngOther130.4 KB 7cb632ce71fe
samples/hallusionbench/img_17_0.pngOther41.2 KB
samples/hallusionbench/img_180_0.pngOther250.2 KB e64a0fe51734
samples/hallusionbench/img_181_0.pngOther250.7 KB f5a5522a8486
samples/hallusionbench/img_182_0.pngOther465.7 KB 383a7f17c228
samples/hallusionbench/img_183_0.pngOther72.7 KB
samples/hallusionbench/img_184_0.pngOther274.5 KB 5e6eaa10c0c2
samples/hallusionbench/img_185_0.pngOther132.3 KB 6416b8c13585
samples/hallusionbench/img_186_0.pngOther275.4 KB f8c19c1fd86d
samples/hallusionbench/img_187_0.pngOther217.2 KB d6cc74ab88c0
samples/hallusionbench/img_188_0.pngOther108.1 KB 355912f42e28
samples/hallusionbench/img_189_0.pngOther427.0 KB 94fce0461d4e
samples/hallusionbench/img_18_0.pngOther41.2 KB
samples/hallusionbench/img_190_0.pngOther339.3 KB c3bca4db56bf
samples/hallusionbench/img_191_0.pngOther519.0 KB 7fe9fe23dd6d
samples/hallusionbench/img_192_0.pngOther347.7 KB 32029085692d
samples/hallusionbench/img_193_0.pngOther332.8 KB 0e4a34e8306a
samples/hallusionbench/img_194_0.pngOther276.6 KB c00e11201202
samples/hallusionbench/img_195_0.pngOther290.3 KB bc1543b7123d
samples/hallusionbench/img_196_0.pngOther490.8 KB ad0a0f126ee4
samples/hallusionbench/img_197_0.pngOther501.2 KB f1a90dcd8733
samples/hallusionbench/img_198_0.pngOther42.9 KB
samples/hallusionbench/img_199_0.pngOther111.0 KB ea841c189d59
samples/hallusionbench/img_19_0.pngOther96.0 KB
samples/hallusionbench/img_1_0.pngOther498.3 KB 9cbc1a5456a8
samples/hallusionbench/img_20_0.pngOther96.1 KB
samples/hallusionbench/img_21_0.pngOther123.3 KB 85a1a8093223
samples/hallusionbench/img_22_0.pngOther125.1 KB e15db0010ffa
samples/hallusionbench/img_23_0.pngOther135.3 KB eacdb331bc4c
samples/hallusionbench/img_24_0.pngOther83.0 KB
samples/hallusionbench/img_25_0.pngOther54.5 KB
samples/hallusionbench/img_26_0.pngOther87.7 KB
samples/hallusionbench/img_27_0.pngOther1.6 MB 1e1272049e90
samples/hallusionbench/img_28_0.pngOther1.6 MB e10a5ff67e0a
samples/hallusionbench/img_29_0.pngOther300.3 KB 0aad5c8ccac4
samples/hallusionbench/img_2_0.pngOther498.3 KB 9cbc1a5456a8
samples/hallusionbench/img_30_0.pngOther134.9 KB 792f540e7fef
samples/hallusionbench/img_31_0.pngOther54.1 KB
samples/hallusionbench/img_32_0.pngOther110.7 KB e6145cd012a7
samples/hallusionbench/img_33_0.pngOther91.9 KB
samples/hallusionbench/img_34_0.pngOther47.5 KB
samples/hallusionbench/img_35_0.pngOther48.7 KB
samples/hallusionbench/img_36_0.pngOther35.2 KB
samples/hallusionbench/img_37_0.pngOther84.0 KB
samples/hallusionbench/img_38_0.pngOther211.4 KB f6079dca955d
samples/hallusionbench/img_39_0.pngOther145.0 KB 99e73f70b5cc
samples/hallusionbench/img_3_0.pngOther356.9 KB 64b7a93c9938
samples/hallusionbench/img_40_0.pngOther65.9 KB
samples/hallusionbench/img_41_0.pngOther51.7 KB
samples/hallusionbench/img_42_0.pngOther109.4 KB b8581d31ddde
samples/hallusionbench/img_43_0.pngOther108.8 KB 2e0c841d6a33
samples/hallusionbench/img_44_0.pngOther77.5 KB
samples/hallusionbench/img_45_0.pngOther59.6 KB
samples/hallusionbench/img_46_0.pngOther59.3 KB
samples/hallusionbench/img_47_0.pngOther77.8 KB
samples/hallusionbench/img_48_0.pngOther40.4 KB
samples/hallusionbench/img_49_0.pngOther40.1 KB
samples/hallusionbench/img_4_0.pngOther356.9 KB 64b7a93c9938
samples/hallusionbench/img_50_0.pngOther40.1 KB
samples/hallusionbench/img_51_0.pngOther40.9 KB
samples/hallusionbench/img_52_0.pngOther53.8 KB
samples/hallusionbench/img_53_0.pngOther53.8 KB
samples/hallusionbench/img_54_0.pngOther54.5 KB
samples/hallusionbench/img_55_0.pngOther54.8 KB
samples/hallusionbench/img_56_0.pngOther54.8 KB
samples/hallusionbench/img_57_0.pngOther51.5 KB
samples/hallusionbench/img_58_0.pngOther51.5 KB
samples/hallusionbench/img_59_0.pngOther48.2 KB
samples/hallusionbench/img_5_0.pngOther85.9 KB
samples/hallusionbench/img_60_0.pngOther47.3 KB
samples/hallusionbench/img_61_0.pngOther393.1 KB c519682106c6
samples/hallusionbench/img_62_0.pngOther465.2 KB 4922388b9c54
samples/hallusionbench/img_63_0.pngOther103.6 KB 3193afb178cc
samples/hallusionbench/img_64_0.pngOther655.7 KB ca0f2268b427
samples/hallusionbench/img_65_0.pngOther1.2 MB 06c4c3566c34
samples/hallusionbench/img_66_0.pngOther140.9 KB 8cc7b55ed374
samples/hallusionbench/img_67_0.pngOther304.5 KB 8b16509078bb
samples/hallusionbench/img_68_0.pngOther296.8 KB e2c1d72a75bf
samples/hallusionbench/img_69_0.pngOther245.1 KB c182549aa440
samples/hallusionbench/img_6_0.pngOther543.4 KB e2c9f51e01ab
samples/hallusionbench/img_70_0.pngOther245.0 KB 3719d828a7e6
samples/hallusionbench/img_71_0.pngOther2.1 MB 3c7bd916b037
samples/hallusionbench/img_72_0.pngOther219.0 KB 55aea267904c
samples/hallusionbench/img_73_0.pngOther202.1 KB 57dafbd20e54
samples/hallusionbench/img_74_0.pngOther238.3 KB 7e74497d3c69
samples/hallusionbench/img_75_0.pngOther633.2 KB 1a3b651aee35
samples/hallusionbench/img_76_0.pngOther296.2 KB 7f7df041ede6
samples/hallusionbench/img_77_0.pngOther993.0 KB 58d786a20f87
samples/hallusionbench/img_78_0.pngOther221.5 KB 8dd27f5afe3a
samples/hallusionbench/img_79_0.pngOther226.6 KB 7c45ded85c25
samples/hallusionbench/img_7_0.pngOther314.9 KB 5ea294005b0b
samples/hallusionbench/img_80_0.pngOther233.5 KB 02d698b417f0
samples/hallusionbench/img_81_0.pngOther43.3 KB
samples/hallusionbench/img_82_0.pngOther16.5 KB
samples/hallusionbench/img_83_0.pngOther9.3 KB
samples/hallusionbench/img_84_0.pngOther1.2 MB 5c3718c719ee
samples/hallusionbench/img_85_0.pngOther41.5 KB
samples/hallusionbench/img_86_0.pngOther50.3 KB
samples/hallusionbench/img_87_0.pngOther88.4 KB
samples/hallusionbench/img_88_0.pngOther64.3 KB
samples/hallusionbench/img_89_0.pngOther84.9 KB
samples/hallusionbench/img_8_0.pngOther425.9 KB fe869647abac
samples/hallusionbench/img_90_0.pngOther44.5 KB
samples/hallusionbench/img_91_0.pngOther41.0 KB
samples/hallusionbench/img_92_0.pngOther189.1 KB 8836b447062c
samples/hallusionbench/img_93_0.pngOther26.8 KB
samples/hallusionbench/img_94_0.pngOther33.2 KB
samples/hallusionbench/img_95_0.pngOther206.6 KB cf109d1ca7e2
samples/hallusionbench/img_96_0.pngOther117.4 KB 47ece21707a5
samples/hallusionbench/img_97_0.pngOther461.9 KB a58e1ee2c0e2
samples/hallusionbench/img_98_0.pngOther572.7 KB 73eeddb2e392
samples/hallusionbench/img_99_0.pngOther123.2 KB 8559accbab2e
samples/hallusionbench/img_9_0.pngOther204.5 KB efa598746e67
samples/hallusionbench/meta.jsonlOther240.2 KB
samples/logicvista/img_0_0.pngOther43.3 KB
samples/logicvista/img_100_0.pngOther23.0 KB
samples/logicvista/img_101_0.pngOther50.9 KB
samples/logicvista/img_102_0.pngOther49.5 KB
samples/logicvista/img_103_0.pngOther16.0 KB
samples/logicvista/img_104_0.pngOther16.0 KB
samples/logicvista/img_105_0.pngOther49.4 KB
samples/logicvista/img_106_0.pngOther49.4 KB
samples/logicvista/img_107_0.pngOther16.2 KB

License and Download

License
Not stated by the source
Access
Open weights, no gate
Download from Zeyuan Yang

Released by Zeyuan Yang through its official repository on Hugging Face.