Benchmarks.bio - SpatialBench-Long: leaderboard
Long-form Benchmarks.bio spatial transcriptomics tasks that require multi-step biological data analysis, tool use, and synthesis over larger assay contexts.
Metric: Pass Rate (%). Source: benchmarks.bio. Saturation forecast: Around 2029. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.5 | 11.11 | #31 |
| 2 | Claude Opus 4.8 | 11.11 | #37 |
| 3 | Gemini 3.5 Flash | 11.11 | #60 |
| 4 | Claude Opus 4.6 | 9.72 | #63 |
| 5 | Claude Opus 4.7 | 8.33 | #49 |
| 6 | Grok 4.20 Beta (0309) (Reasoning) | 6.94 | #204 (Grok 4.20 Beta (0309)) |
| 7 | GPT-5.4 | 5.56 | #79 |
| 8 | Kimi K2.6 | 5.56 | #104 |
| 9 | Gemini 3.1 Pro (Preview) | 4.17 | #58 |
| 10 | Claude Sonnet 4.6 | 4.17 | #90 |
| 11 | Grok 4.3 | 4.17 | #188 |
| 12 | Gemini 2.5 Pro | 1.39 | #152 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=benchmarks-bio-spatialbench-long · How It Works · Data refreshed daily, snapshot 2026-10-20.