PROBE Semantic Similarity: leaderboard
Correlation between protein-embedding similarities and Gene Ontology semantic similarities (MF, BP, CC aspects), a PROBE protein-representation task from Hacettepe University's HUBioDataLab (2022).
Metric: Average Correlation. Source: huggingface.co. 21 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 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 It Works · Data refreshed daily, snapshot 2026-10-20.