Axiom Bio morphology-to-molecule matching (Morphology-to-molecule matching)
We show this table for reference; we do not rank on it.
Matches multi-channel cellular imaging data to the molecule-dose perturbations that produced it.
Benchmark score on Morphology-to-molecule matching — November 13, 2026
We compile the Morphology-to-molecule matching rows from provider self-reports. Claude Mythos 5.2 leads the table at 35.2%, followed by Claude Opus 5.5 (34.0%) and Gemini 4 Argon (25.2%). We do not use these results to rank models overall.
Claude Mythos 5.2
Anthropic
Reported by AnthropicClaude Opus 5.5
Anthropic
Reported by AnthropicGemini 4 Argon
5 modelsKnowledgeCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (5 models)
None of the 5 results on this page has a documented run by the benchmark or an independent evaluator: 3 reported by the labs that built the models and 2 reported in another publisher’s document.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Claude Mythos 5.2AnthropicReported by Anthropic | 35.2% | Reported by Anthropic | Not reported | Closed |
| 2 | Claude Opus 5.5AnthropicReported by Anthropic | 34.0% | Reported by Anthropic | Not reported | Closed |
| 3 | Gemini 4 ArgonGoogleLab-reported, from another publisher’s document | 25.2% | Lab-reported, from another publisher’s document | Not reported | Closed |
| 4 | Claude Sonnet 5.5AnthropicReported by Anthropic | 25.0% | Reported by Anthropic | Not reported | Closed |
| 5 | GPT-6 AstraOpenAILab-reported, from another publisher’s document | 22.8% | Lab-reported, from another publisher’s document | Not reported | Closed |
- Lab-reported
- Benchmark-run
- Independent
Among the reported Morphology-to-molecule matching rows, Claude Mythos 5.2 is first at 35.2%. The third row is 10.0 points behind. The broader top-10 range is 12.4 points, so the table still separates the published systems.
5 models have been evaluated on Morphology-to-molecule matching. The benchmark falls in the Knowledge category. Morphology-to-molecule matching is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About Morphology-to-molecule matching
Year
2026
Tasks
Four multi-channel cell-imaging perturbation-matching tasks
Format
Matching accuracy
Difficulty
Biomedical image and molecular reasoning
Section 8.17.3 reports a provider-run result in a closed sandbox with imaging data, code execution, and no network access. It is display-only evidence.
Freshness and provenance
Version
Morphology-to-molecule matching 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 Morphology-to-molecule matching measure?
Matches multi-channel cellular imaging data to the molecule-dose perturbations that produced it.
Which model scores highest on Morphology-to-molecule matching?
Claude Mythos 5.2 by Anthropic currently leads with a score of 35.2% on Morphology-to-molecule matching.
How many models are evaluated on Morphology-to-molecule matching?
5 AI models have published results on Morphology-to-molecule matching in the BenchLM catalog.
Compare top models on Morphology-to-molecule matching
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.