Protein domain identification (Protein Domain ID)
We show this table for reference; we do not rank on it.
Anthropic's protein-understanding test: from an amino acid sequence alone, choose the correct Pfam domain family among similar distractors, without tools.
Benchmark score on Protein Domain ID — November 11, 2026
We compile the Protein Domain ID rows from provider self-reports. Claude Mythos 5.2 leads the table at 91.8%, followed by Claude Opus 5.5 (73.6%) and Claude Mythos 5.1 (63.5%). We do not use these results to rank models overall.
Claude Mythos 5.2
Anthropic
Claude Opus 5.5
Anthropic
Claude Mythos 5.1
Anthropic
3 modelsKnowledgeCurrentDisplay onlyUpdated November 11, 2026
Benchmark score table (3 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Claude Mythos 5.2Anthropic | 91.8% | Not reported | Closed |
| 2 | Claude Opus 5.5Anthropic | 73.6% | Not reported | Closed |
| 3 | Claude Mythos 5.1Anthropic | 63.5% | Not reported | Closed |
Among the reported Protein Domain ID rows, Claude Mythos 5.2 is first at 91.8%. The third row is 28.3 points behind. The broader top-10 range is 28.3 points, so the table still separates the published systems.
3 models have been evaluated on Protein Domain ID. The benchmark falls in the Knowledge category. Protein Domain ID is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About Protein Domain ID
Year
2026
Tasks
Multiple-choice Pfam family questions
Format
Accuracy
Difficulty
Protein understanding
Introduced in the Claude Fable 5.2 and Mythos 5.2 system card and run on Mythos 5.2 with biology safeguards off. Internal, so display-only.
Freshness and provenance
Version
Protein Domain ID 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
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.
Questions
What does Protein Domain ID measure?
Anthropic's protein-understanding test: from an amino acid sequence alone, choose the correct Pfam domain family among similar distractors, without tools.
Which model scores highest on Protein Domain ID?
Claude Mythos 5.2 by Anthropic currently leads with a score of 91.8% on Protein Domain ID.
How many models are evaluated on Protein Domain ID?
3 AI models have published results on Protein Domain ID in the BenchLM catalog.
Compare top models on Protein Domain ID
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.