Protein Design (Anthropic)
Models generate novel protein sequences under design constraints and rank protein design libraries for experimental testing.
Reported as two tasks, Sequence Generation and Library Ranking, with no overall score.
- Made by
- Anthropic
- Released
- June 2026
- Kind
- Research science
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- Kept private
- Strongest model tested
- Claude Opus 5 #10 on the capability index
- Last in a system card
- October 2026
- Last model added
- October 2026
Claude Opus 5 leads with 42.5%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 Claude Opus 5 42.5%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 | 42.5% | Jul 2026 | Lab model card |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
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.
5 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 |
|---|---|---|---|---|
| Oct 7, 2026 | Claude Haiku 5.5 system card | Protein design, Sequence Generation 33.1 and Library Ranking 45.3, no overall (8.13.4) | Capabilities | |
| Sep 28, 2026 | Claude Sonnet 5.5 system card | Protein Design, Sequence Generation 51.0% and Library Ranking 54.8%, no overall (8.17.5, Figure 8.17.A) | Capabilities | |
| Sep 22, 2026 | Claude Opus 5.5 system card | Protein design, Sequence Generation 60.2% and Library Ranking 56.0%, no overall (8.17.5) | Capabilities | |
| Sep 1, 2026 | Claude Fable 5.1 system card | Protein Design, Sequence Generation 46.0% and Library Ranking 49.3%, no overall, Mythos 5.1 (8.19.4) | Other | |
| Jul 24, 2026 | Claude Opus 5 system card | 42.5 | Protein Design, single score for constraint satisfaction, folding confidence and novelty, no tools (8.17.4) | 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%