SAVRN Model Hub · Comparisons
bge-base-en-v1.5 vs SapBERT-from-PubMedBERT-fulltext
Bge-base-en-v1.5 has 109M parameters and SapBERT-from-PubMedBERT-fulltext has 109M parameters; bge-base-en-v1.5 is released under MIT License and SapBERT-from-PubMedBERT-fulltext under Apache License 2.0; at 16-bit, bge-base-en-v1.5 needs about 0.3 GB (1x MI300X from $1.85 an hour) and SapBERT-from-PubMedBERT-fulltext about 0.3 GB (1x MI300X from $1.85 an hour).
| Field | bge-base-en-v1.5 BAAI/bge-base-en-v1.5 | SapBERT-from-PubMedBERT-fulltext cambridgeltl/SapBERT-from-PubMedBERT-fulltext |
|---|---|---|
| Publisher | Beijing Academy of Artificial Intelligence | Language Technology Lab @University of Cambridge |
| Task | Feature extraction | Feature extraction |
| Modality | Text | Text |
| Parameters, as reported | 109M parameters | 109M parameters |
| Architecture | BertModel | BertModel |
| Library | sentence-transformers | transformers |
| Context length | 512 tokens | 512 tokens |
| Repository size | 1.3 GB | 1.8 GB |
| Artifact formats | safetensors, onnx, pytorch | safetensors, pytorch, jax, tf |
| License | mit | apache-2.0 |
| Access | Open weights, no gate | Open weights, no gate |
| Memory at 16-bit (weights and margin) | 0.3 GB | 0.3 GB |
| Cheapest GPUs at 16-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Memory at 4-bit (weights and margin) | 0.1 GB | 0.1 GB |
| Cheapest GPUs at 4-bit, per hour | 1x MI300X, $1.85 | 1x MI300X, $1.85 |
| Revision viewed | a5beb1e3e68b | 090663c3ae57 |
| Downloads reported by the hub | 10.5M | 1.5M |
| Last observed | 2026-09-18 | 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.
bge-base-en-v1.5
| Benchmark | Conditions | Result | Reported by | Revision | Date |
|---|---|---|---|---|---|
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 76.1493 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric apComparison conditions not established | 39.3234 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonCounterfactualClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 70.169 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric accuracyComparison conditions not established | 93.3868 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric apComparison conditions not established | 90.2128 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonPolarityClassification | Configuration defaultTask ClassificationMetric f1Comparison conditions not established | 93.3774 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric accuracyComparison conditions not established | 48.846 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB AmazonReviewsClassification (en) | Configuration enTask ClassificationMetric f1Comparison conditions not established | 48.1465 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1Comparison conditions not established | 40.754 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_10Comparison conditions not established | 55.761 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_100Comparison conditions not established | 56.331 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_1000Comparison conditions not established | 56.334 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_3Comparison conditions not established | 51.92 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric map_at_5Comparison conditions not established | 54.011 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1Comparison conditions not established | 41.181 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_10Comparison conditions not established | 55.968 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_100Comparison conditions not established | 56.538 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_1000Comparison conditions not established | 56.542 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_3Comparison conditions not established | 51.98 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric mrr_at_5Comparison conditions not established | 54.209 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1Comparison conditions not established | 40.754 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_10Comparison conditions not established | 63.605 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_100Comparison conditions not established | 66.052 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_1000Comparison conditions not established | 66.12 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_3Comparison conditions not established | 55.708 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric ndcg_at_5Comparison conditions not established | 59.452 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1Comparison conditions not established | 40.754 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_10Comparison conditions not established | 8.841 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_100Comparison conditions not established | 0.991 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_1000Comparison conditions not established | 0.1 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_3Comparison conditions not established | 22.238 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric precision_at_5Comparison conditions not established | 15.149 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1Comparison conditions not established | 40.754 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_10Comparison conditions not established | 88.407 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_100Comparison conditions not established | 99.147 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_1000Comparison conditions not established | 99.644 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_3Comparison conditions not established | 66.714 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArguAna | Configuration defaultTask RetrievalMetric recall_at_5Comparison conditions not established | 75.747 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArxivClusteringP2P | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 48.7488 | BAAI Publisher reported |
Evaluated revision not stated | — |
| MTEB ArxivClusteringS2S | Configuration defaultTask ClusteringMetric v_measureComparison conditions not established | 42.8076 | BAAI Publisher reported |
Evaluated revision not stated | — |
SAVRN's Notes on bge-base-en-v1.5
If the plan is to embed a corpus once and query it for years, hardware is the smallest decision. At 16-bit the weights take 0.2 GB and the run needs 0.3 GB; at 8-bit and 4-bit both round to 0.1 GB. The cheapest listing, one MI300X with 192 GB at $1.85 per hour on-demand, is the smallest unit a host sells, not what a 109M-parameter, 12-layer BERT encoder needs; the 1.3 GB float32 checkpoint and what you co-locate matter more.
The MIT terms permit commercial use, modification and redistribution and ask only that the copyright and permission notices ride along. Check the 512-token context first; longer passages need chunking. The publisher's own note points anyone needing more languages at bge-m3, 100 plus of them. The scores shown are the publisher's own MTEB results, such as 93.39 accuracy on AmazonPolarityClassification, so run your own set before relying on them.
SAVRN's Notes on SapBERT-from-PubMedBERT-fulltext
One vector per biomedical entity name is the entire output of SapBERT-from-PubMedBERT-fulltext, and that narrow job is why it draws 1.5 million downloads a month four years after its March 2, 2022 release. Cambridge's Language Technology Lab trained it on UMLS 2020AA, English only, on a PubMedBERT base, and the [CLS] embedding of the last layer is the feature you keep. At 109 million parameters it needs 0.3 GB at 16-bit and 0.1 GB at 8-bit or 4-bit, so an entity-linking service runs on a sliver of the $1.85-an-hour MI300X on the Index.
Apache 2.0 permits commercial use, modification and redistribution with the notices intact. Two checks before you build on it: the 512-token context means inputs are entity names, not passages, and the last update was June 14, 2023, with the method in arXiv:2010.11784. Weights ship in safetensors, pytorch, jax and tf, so the serving stack is your call.
Questions
Which is larger, bge-base-en-v1.5 or SapBERT-from-PubMedBERT-fulltext?
bge-base-en-v1.5 (109M parameters) is larger than SapBERT-from-PubMedBERT-fulltext (109M parameters), by the parameter counts their publishers report.
Which is cheaper to run, bge-base-en-v1.5 or SapBERT-from-PubMedBERT-fulltext?
At 4-bit, bge-base-en-v1.5 fits on 1x MI300X from $1.85 an hour and SapBERT-from-PubMedBERT-fulltext on 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use bge-base-en-v1.5 commercially?
Yes. bge-base-en-v1.5 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 SapBERT-from-PubMedBERT-fulltext commercially?
Yes. SapBERT-from-PubMedBERT-fulltext is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.