LatchBio SpatialBench (Anthropic): leaderboard
Anthropic system-card run of LatchBio SpatialBench, measuring spatial transcriptomics analysis workflows.
Metric: Score (%). Source: www-cdn.anthropic.com. Saturation forecast: Around 2028. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Mythos Preview | 53.8 | #4 |
| 2 | Claude Opus 4.8 | 53.3 | #37 |
| 3 | Claude Opus 4.7 | 51.4 | #49 |
| 4 | Claude Sonnet 4.6 | 48.7 | #90 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=latchbio-spatialbench-anthropic · How It Works · Data refreshed daily, snapshot 2026-10-20.