BlogLLM Benchmark Scores as Published, Side by Side
De novo protein binder design (Anthropic internal): Results as Published
Every result the catalog holds for De novo protein binder design (Anthropic internal): 5 models from 1 developer, read from 2 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Science and MathMaintainer Anthropic (internal evaluation)Introduced 2026Data version 2026103001, as of 2026-10-30
Extended protein design campaign: for each of 15 targets, 24 hours of wall-clock time to design 30 miniprotein binders.
De novo binder design
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| Claude Sonnet 5.5Anthropic, released 2026-09-28 | 82.3% | Anthropic, Claude Sonnet 5.5 System Cardchecked 2026-10-19 | Effort: max; Context: Agent campaign, 24 hours per target |
| Claude Opus 5.5Anthropic, released 2026-09-22 | 82.6% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25; printed on 1 more page | - |
| Claude Mythos 5.1Anthropic, released 2026-09-01 | 79.1% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Opus 5Anthropic, released 2026-07-24 | 78.9% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
| Claude Sonnet 5Anthropic, released 2026-06-30 | 72.6% | Anthropic, Claude Opus 5.5 System Cardchecked 2026-10-25 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.