Skip to main content

Benchmark profile

Anthropic Protein Design evaluation (Protein Design)

Generates novel protein sequences under family, topology, globularity, and structural-motif constraints.

Data verified

Benchmark score on Protein Design — July 24, 2026

BenchLM mirrors the published score view for Protein Design. Claude Opus 5 leads the public snapshot at 42.5%. BenchLM does not use these results to rank models overall.

1 modelKnowledgeCurrentDisplay onlyUpdated July 24, 2026

Benchmark score table (1 model)

Score
1
Claude Opus 5Anthropic · Closed
42.5%

About Protein Design

Year

2026

Tasks

Constrained protein-sequence design tasks

Format

Composite score

Difficulty

Computational protein design

Section 8.17.4 reports a composite of constraint satisfaction, folding confidence, and sequence novelty without tool access.

BenchLM freshness & provenance

Version

Protein Design 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does Protein Design measure?

Generates novel protein sequences under family, topology, globularity, and structural-motif constraints.

Which model scores highest on Protein Design?

Claude Opus 5 by Anthropic currently leads with a score of 42.5% on Protein Design.

How many models are evaluated on Protein Design?

1 AI models have been evaluated on Protein Design on BenchLM.

Last updated: July 24, 2026 · BenchLM version Protein Design 2026