PROBE Semantic Similarity — leaderboard
PROBE Semantic Similarity evaluates model capability on science tasks from the linked upstream source with similarity corr ave as the primary reported metric.
Metric: Average Correlation. Source: huggingface.co. 21 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | ESM-1b | 0.61 |
| 2 | ProtXLNet | 0.61 |
| 3 | Mut2Vec | 0.51 |
| 4 | UniRep | 0.41 |
| 5 | Learned-Vec | 0.4 |
| 6 | SeqVec | 0.4 |
| 7 | ProtT5-XL | 0.39 |
| 8 | TCGA-Embedding | 0.36 |
| 9 | MSA-Transformer | 0.33 |
| 10 | ProtBERT-BFD | 0.33 |
Interactive version: theaggregate.ai/benchmark?slug=probe-semantic-similarity · How the rankings work · Data refreshed daily, snapshot 2026-07-22.