SAVRN Model Hub · Comparisons
DeepSeek-V3.2 vs GLM-5.2
DeepSeek-V3.2 has 685.4B parameters and GLM-5.2 has 753.3B parameters; both are released under MIT License; at 16-bit, DeepSeek-V3.2 needs about 1644.9 GB (7x MI325X from $14.00 an hour) and GLM-5.2 about 1808 GB (8x MI325X from $16.00 an hour).
| Field | DeepSeek-V3.2 deepseek-ai/DeepSeek-V3.2 | GLM-5.2 zai-org/GLM-5.2 |
|---|---|---|
| Publisher | DeepSeek | Z.ai |
| Task | Text generation | Text generation |
| Modality | Text | Text |
| Parameters, as reported | 685.4B parameters | 753.3B parameters |
| Architecture | DeepseekV32ForCausalLM | GlmMoeDsaForCausalLM |
| Library | transformers | transformers |
| Context length | 163,840 tokens | 1,048,576 tokens |
| Repository size | 689.5 GB | 1.5 TB |
| Artifact formats | safetensors | safetensors |
| License | mit | mit |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 1644.9 GB | 1808 GB |
| Cheapest GPUs at 16-bit, per hour | 7x MI325X, $14.00 | 8x MI325X, $16.00 |
| Memory at 4-bit (weights and margin) | 411.2 GB | 452 GB |
| Cheapest GPUs at 4-bit, per hour | 2x MI325X, $4.00 | 2x MI325X, $4.00 |
| Revision viewed | a7e62ac04ecb | cf457fa734ab |
| Downloads reported by the hub | 2.4M | 988.5k |
| Last observed | 2026-09-20 | 2026-09-18 |
An evaluation row appears only where at least two of these models report the same benchmark with the same stated configuration, metric, unit and setup. Different evaluators stay named in each cell. Values are shown as reported: no unit conversion, no ranking.
Other Reported Results
These results are listed for each model on its own, because the conditions needed to compare them are not stated or do not match. Two results that leave a condition blank are not assumed to share it.
DeepSeek-V3.2
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| claw-eval/Claw-Eval | Task generalMetric generalSetup Pass³% | N=3 | 161 tasksComparison conditions not established | 42.2 | Claw-Eval Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-04-23 |
| claw-eval/Claw-Eval | Task multi_turnMetric multi_turnSetup Pass³% | N=3 | 38 tasksComparison conditions not established | 31.6 | Claw-Eval Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-04-23 |
| internlm/WildClawBench | Task avg_costMetric avg_costComparison conditions not established | 11.4 | WildClawBench Reported by a third party |
Evaluated revision not stated | 2026-05-22 |
| internlm/WildClawBench | Task avg_timeMetric avg_timeComparison conditions not established | 549 | WildClawBench Reported by a third party |
Evaluated revision not stated | 2026-05-22 |
| internlm/WildClawBench | Task overallMetric overallComparison conditions not established | 34 | WildClawBench Reported by a third party |
Evaluated revision not stated | 2026-05-22 |
| open-agent-leaderboard/results | Task appworldMetric appworldSetup agent: React + ShortlistingComparison conditions not established | 0.04 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task appworldMetric appworldSetup agent: OpenAI SoloComparison conditions not established | 0.06 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task appworldMetric appworldSetup agent: SmolagentComparison conditions not established | 0.13 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task appworldMetric appworldSetup agent: Claude CodeComparison conditions not established | 0.03 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task appworldMetric appworldSetup agent: ReactComparison conditions not established | 0.09 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task browsecomp_plusMetric browsecomp_plusSetup agent: SmolagentComparison conditions not established | 0.21 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task browsecomp_plusMetric browsecomp_plusSetup agent: OpenAI SoloComparison conditions not established | 0.3 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task browsecomp_plusMetric browsecomp_plusSetup agent: Claude CodeComparison conditions not established | 0.48 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task browsecomp_plusMetric browsecomp_plusSetup agent: React + ShortlistingComparison conditions not established | 0.36 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task browsecomp_plusMetric browsecomp_plusSetup agent: ReactComparison conditions not established | 0.36 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task overallMetric overallSetup agent: ReactComparison conditions not established | 0.4585 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task overallMetric overallSetup agent: React + ShortlistingComparison conditions not established | 0.446 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task overallMetric overallSetup agent: Claude CodeComparison conditions not established | 0.4158 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task overallMetric overallSetup agent: OpenAI SoloComparison conditions not established | 0.3217 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task overallMetric overallSetup agent: SmolagentComparison conditions not established | 0.4092 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task swebenchMetric swebenchSetup agent: OpenAI SoloComparison conditions not established | 0.7368 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task swebenchMetric swebenchSetup agent: SmolagentComparison conditions not established | 0.56 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task swebenchMetric swebenchSetup agent: React + ShortlistingComparison conditions not established | 0.6875 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task swebenchMetric swebenchSetup agent: ReactComparison conditions not established | 0.6875 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task swebenchMetric swebenchSetup agent: Claude CodeComparison conditions not established | 0.64 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_airlineMetric taubench_airlineSetup agent: React + ShortlistingComparison conditions not established | 0.56 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_airlineMetric taubench_airlineSetup agent: SmolagentComparison conditions not established | 0.6 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_airlineMetric taubench_airlineSetup agent: ReactComparison conditions not established | 0.56 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_airlineMetric taubench_airlineSetup agent: OpenAI SoloComparison conditions not established | 0.2 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_airlineMetric taubench_airlineSetup agent: Claude CodeComparison conditions not established | 0.28 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_retailMetric taubench_retailSetup agent: SmolagentComparison conditions not established | 0.77 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_retailMetric taubench_retailSetup agent: Claude CodeComparison conditions not established | 0.65 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_retailMetric taubench_retailSetup agent: React + ShortlistingComparison conditions not established | 0.82 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_retailMetric taubench_retailSetup agent: ReactComparison conditions not established | 0.82 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_retailMetric taubench_retailSetup agent: OpenAI SoloComparison conditions not established | 0.19 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_telecomMetric taubench_telecomSetup agent: Claude CodeComparison conditions not established | 0.61 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_telecomMetric taubench_telecomSetup agent: React + ShortlistingComparison conditions not established | 0.71 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_telecomMetric taubench_telecomSetup agent: SmolagentComparison conditions not established | 0.84 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_telecomMetric taubench_telecomSetup agent: ReactComparison conditions not established | 0.71 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
| open-agent-leaderboard/results | Task taubench_telecomMetric taubench_telecomSetup agent: OpenAI SoloComparison conditions not established | 0.18 | Open Agent Leaderboard Reported by a third party |
Evaluated revision not stated | 2026-05-18 |
GLM-5.2
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| Idavidrein/gpqa | Task diamondMetric diamondComparison conditions not established | 91.2 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-06-22 |
| IntelligenceLab/Long-Horizon-Terminal-Bench | Task lhtb_solvedMetric lhtb_solvedSetup 1/46 tasks solved at reward >= 0.95 ([email protected]); mean reward x100 = 31.6; official LHTB Harbor harnessComparison conditions not established | 1 | LHTB leaderboard Reported by a third party |
Evaluated revision not stated | 2026-07-16 |
| InternScience/ResearchClawBench | Task overallMetric overallSetup ResearchHarness evaluation with tools enabled, code execution, and a file-system workspace; completed 39/40 ResearchClawBench tasks.Comparison conditions not established | 20.7092 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-06-23 |
| ScaleAI/SWE-bench_Pro | Task SWE_Bench_ProMetric SWE_Bench_ProComparison conditions not established | 62.1 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-06-22 |
| cais/hle | Task hleMetric hleSetup With toolsComparison conditions not established | 54.7 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-06-22 |
| crosbylegal/RedlineBench | Task redline_overallMetric redline_overallSetup agent=glm-5.2; 3-LLM judge panel (majority vote); turn-weighted weighted pass rate (0-100); post-publication runComparison conditions not established | 45.7 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-06-19 |
| datacurve/deep-swe | Task deep_sweMetric deep_sweComparison conditions not established | 46.2 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-06-22 |
| harborframework/terminal-bench-2.1 | Task terminalbench_2_1Metric terminalbench_2_1Setup Best reported harness: Claude Code 2.1.167 (temperature=1.0, top_p=0.95, max_new_tokens=131072, no wall-clock limit, averaged over 5 runs).Comparison conditions not established | 82.7 | Model Card Reported by a third party |
Evaluated revision not stated | 2026-07-02 |
| internlm/WildClawBench | Task avg_costMetric avg_costComparison conditions not established | 17.1 | WildClawBench Reported by a third party |
Evaluated revision not stated | 2026-08-11 |
| internlm/WildClawBench | Task avg_timeMetric avg_timeComparison conditions not established | 442 | WildClawBench Reported by a third party |
Evaluated revision not stated | 2026-08-11 |
| internlm/WildClawBench | Task overallMetric overallComparison conditions not established | 54.2 | WildClawBench Reported by a third party |
Evaluated revision not stated | 2026-08-11 |
| joelniklaus/LEXam-hard | Task lexam_hardMetric lexam_hardSetup lighteval, LEXam paper prompts, one response per question, no tools; DeepSeek-R1-0528 judge; mean of the German and English means over the 518 questions, 0-100Comparison conditions not established | 37.55 | SwissLegalEvals per-sample details (lighteval) Reported by a third party |
Evaluated revision not stated | 2026-06-24 |
SAVRN's Notes on DeepSeek-V3.2
DeepSeek-V3.2 is one of the largest open-weight models anyone can download: 685B parameters in a mixture-of-experts design, with DeepSeek Sparse Attention to keep long contexts affordable and a 163,840-token window. It is built for reasoning and agent work, and 2.3 million downloads a month show real adoption.
Running it yourself is a data center decision. At 16-bit it needs about 1.6 TB of accelerator memory, which by our SAVRN Index prices means seven MI325X cards at about $14 an hour on demand; at 4-bit, two cards at about $4. The MIT license allows commercial use with no strings beyond the notice, which makes it one of the most permissive frontier-class options available.
SAVRN's Notes on GLM-5.2
Plan the storage before anything else: the weights arrive as 295 safetensors files totaling about 1.5 TB. Z.ai built GLM-5.2 for long-horizon tasks on a 1,048,576-token context, with 753.3B parameters spread across 78 layers and 256 routed experts. At 4-bit the weights shrink to 376.7 GB and the run needs 452 GB, which fits 2x MI325X with 256 GB each at $4.00 an hour on-demand, the cheapest setup in our table. Full 16-bit needs 1,808 GB and 8x MI325X at $16.00 an hour.
MIT lets you run it commercially, modify it and redistribute it with the notices intact; the publisher names SGLang v0.5.13.post1 or later and vLLM v0.23 for serving. Weigh that $4.00 an hour against the Index hosts: DeepInfra at $0.75 in and $2.40 out per million tokens, four others at $1.40 and $4.40, Scaleway at $2.05 and $6.27. Your token volume decides which side wins.
Questions
Which is larger, DeepSeek-V3.2 or GLM-5.2?
GLM-5.2 (753.3B parameters) is larger than DeepSeek-V3.2 (685.4B parameters), by the parameter counts their publishers report.
Which is cheaper to run, DeepSeek-V3.2 or GLM-5.2?
At 4-bit, DeepSeek-V3.2 fits on 2x MI325X from $4.00 an hour and GLM-5.2 on 2x MI325X from $4.00 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use DeepSeek-V3.2 commercially?
Yes. DeepSeek-V3.2 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.
Can I use GLM-5.2 commercially?
Yes. GLM-5.2 is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.