GeneBench — leaderboard
Genetics and quantitative-biology benchmark where models analyze noisy scientific data, detect confounders, and implement statistical workflows with minimal guidance.
Metric: Mean pass rate (self-reported). Source: benchmarklist.com. Status: saturation imminent. 16 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 Pro | 33.2 |
| 2 | GPT-5.4 Pro (xHigh) | 25.6 |
| 3 | GPT-5.5 (xHigh) | 25 |
| 4 | GPT-5.4 (xHigh) | 19 |
| 5 | Gemini 3.1 Pro (Preview) (High) | 11.2 |
| 6 | GPT-5.2 Pro | 10.8 |
| 7 | GPT-5.2 (xHigh) | 9.4 |
| 8 | GLM-5.1 | 4.2 |
| 9 | GPT-5 Pro | 4 |
| 10 | GPT-5 (High) | 3.5 |
| 11 | MiMo-V2.5-Pro | 3 |
| 12 | Qwen 3.6 Plus | 2.7 |
| 13 | Grok 4.20 | 2.1 |
| 14 | MiMo-V2-Pro | 1.6 |
Interactive version: theaggregate.ai/benchmark?slug=genebench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.