ProteinGym
Deep mutational scanning benchmarks. The model ranks mutations by predicted effect on protein function, scored by Spearman rank correlation with lab measurements. Anthropic reports a hard subset, as the correlation times 100.
The repo has releases PG_v1.0 to PG_v1.3 (April 2025) that add assays, so check which version a score used. Anthropic system cards report a ProteinGym Hard subset.
- Made by
- OATML (Oxford) + Marks Lab (Harvard)
- Released
- December 2023
- Kind
- Research science
- Level
- Research frontier
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Last in a system card
- September 2026
- Last model added
- September 2026
4
System cards report it, from 1 lab
No scores here yet
We have no scores for ProteinGym yet.
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
4 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Sep 1, 2026 | Claude Fable 5.1 system card | 49.3 | ProteinGym Hard, Mythos 5.1 | Other |
| Jul 24, 2026 | Claude Opus 5 system card | 47.7 | ProteinGym Hard, rank correlation with lab measurements reported as a percentage (8.17.3) | Capabilities |
| Jun 30, 2026 | Claude Sonnet 5 system card | 37 | ProteinGym Hard, score 0.37 (8.14.4, Figure 8.14.6.A) | Capabilities |
| May 28, 2026 | Claude Opus 4.8 system card | 39.6 | ProteinGym Hard, rank correlation with lab measurements reported as 39.6% (8.16.5) | Capabilities |
More in Science and reasoning
- GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics.
Gemini 4 Carbon 96.5% - Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
- FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics.
Intern-S2-397B 87% - BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
- HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels. Gemini 3 Pro 78.3%
- LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%