ProteinGym Hard · System-card Hard subset; exact task count not stated · Benchmark definition and scores
ProteinGym Hard · System-card Hard subset; exact task count not stated has benchmark disclosures or scores across 2 model releases.
Benchmark versions and metrics
Aliases ProteinGym Hard
- Rank correlation with experimental measurements · % · Higher is better
- 任务特定分数(原文 0–1) · 0-1 · Higher is better
Latest models by series · reported scores
The latest models in each named series have no scores to display in this scope. Recorded historical data appears below.
History · 2 releases
- Claude Opus 51 score record for this release, including 1 exact value (may include historical records)
- Claude Sonnet 51 score record for this release, including 1 exact value (may include historical records)