BioSimBench 1.0: Drug response
Science
Perturbation-specific F1 on 60 held-out cases predicting a drug's transcriptional response at a given dose.
Benchmark source: Celltype
Top models (higher is better)
| Model | Score | Source |
|---|---|---|
| Gemini 4 Argon | 10.3 | BioSimBench 1.0: Gemini 4 Argon · CellType |
| Gemini 3.8 Flash | 10.0 | BioSimBench 1.0: Gemini 3.8 Flash · CellType |
| Gemini 3.1 Pro Preview | 9.9 | BioSimBench 1.0: Gemini 3.1 Pro · CellType |
| Claude Opus 5.5 | 9.5 | BioSimBench 1.0: Claude Opus 5.5 · CellType |
| GPT-6 Astra | 9.3 | BioSimBench 1.0: GPT-6 Astra · CellType |
| GPT-6.1 Sol | 9.1 | BioSimBench 1.0: GPT-6.1 Sol · CellType |
| GPT-6 Sol | 9.1 | BioSimBench 1.0: GPT-6 Sol · CellType |
| Claude Haiku 5.5 | 8.6 | BioSimBench 1.0: Claude Haiku 5.5 · CellType |
| Claude Sonnet 5.5 | 8.5 | BioSimBench 1.0: Claude Sonnet 5.5 · CellType |
| Grok 4.7 | 8.3 | BioSimBench 1.0: Grok 4.7 · CellType |
| GPT-6 Luna | 8.1 | BioSimBench 1.0: GPT-6 Luna · CellType |