LatchBio SingleCellBench (SingleCellBench)
We show this table for reference; we do not rank on it.
Single-cell RNA sequencing analysis tasks spanning common bioinformatics workflows.
Benchmark score on SingleCellBench — November 13, 2026
We compile the SingleCellBench rows from provider self-reports. Claude Mythos 5.2 leads the table at 65.6%, followed by Claude Mythos 5.1 (61.8%) and Claude Opus 5.5 (61.2%). We do not use these results to rank models overall.
Claude Mythos 5.2
Anthropic
Reported by AnthropicClaude Mythos 5.1
Anthropic
Reported by AnthropicClaude Opus 5.5
Anthropic
Reported by Anthropic5 modelsKnowledgeCurrentDisplay onlyUpdated November 13, 2026
Benchmark score table (5 models)
All 5 results on this page were reported by the labs that built the models.
| Rank | Model / configuration | Score | Who ran it | Parameters (B) | Open / closed |
|---|---|---|---|---|---|
| 1 | Claude Mythos 5.2AnthropicReported by Anthropic | 65.6% | Reported by Anthropic | Not reported | Closed |
| 2 | Claude Mythos 5.1AnthropicReported by Anthropic | 61.8% | Reported by Anthropic | Not reported | Closed |
| 3 | Claude Opus 5.5AnthropicReported by Anthropic | 61.2% | Reported by Anthropic | Not reported | Closed |
| 4 | Claude Opus 5AnthropicReported by Anthropic | 60.6% | Reported by Anthropic | Not reported | Closed |
| 5 | Claude Sonnet 5.5AnthropicReported by Anthropic | 59.1% | Reported by Anthropic | Not reported | Closed |
- Lab-reported
- Benchmark-run
- Independent
Among the reported SingleCellBench rows, Claude Mythos 5.2 is first at 65.6%. The third row is 4.4 points behind. The broader top-10 range is 6.5 points, so many of the published results sit in a relatively narrow band.
5 models have been evaluated on SingleCellBench. The benchmark falls in the Knowledge category. SingleCellBench is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About SingleCellBench
Year
2026
Tasks
195 single-cell RNA sequencing problems
Format
Task score
Difficulty
Professional bioinformatics
Section 8.17.2 reports this provider-run result as display-only life-science evidence.
Freshness and provenance
Version
SingleCellBench 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 SingleCellBench measure?
Single-cell RNA sequencing analysis tasks spanning common bioinformatics workflows.
Which model scores highest on SingleCellBench?
Claude Mythos 5.2 by Anthropic currently leads with a score of 65.6% on SingleCellBench.
How many models are evaluated on SingleCellBench?
5 AI models have published results on SingleCellBench in the BenchLM catalog.
Compare top models on SingleCellBench
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.