TwinLab-Bench - Pass Rate: leaderboard
TwinLab-Bench (arXiv 2611.26248) scientific experimentation benchmark (Pass Rate) across 52 tasks in agentic twins of real laboratories.
Metric: Task Pass Rate (%, out of 52 tasks). Source: huggingface.co. Saturation forecast: Around May 2028. 13 models tracked. Updated 22 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Claude Fable 5.2 | High | 46.15 | #2 |
| 2 | Claude Opus 5.5 | High | 42.31 | #9 |
| 3 | GPT-6 Astra | High | 32.69 | #11 |
| 4 | GPT-6.1 Sol | High | 32.69 | #15 |
| 5 | Claude Sonnet 5.5 | High | 30.77 | #24 |
| 6 | DeepSeek V4.1 Flash (1017) | High | 21.15 | #48 |
| 7 | GLM-5.3 | High | 21.15 | #79 |
| 8 | Kimi K3.1 Pro | High | 19.23 | #35 |
| 9 | MiMo-V2.6-Pro | High | 19.23 | #94 |
| 10 | hy4 | High | 13.46 | #44 |
| 11 | Qwen 3.8 Max | High | 13.46 | #67 |
| 12 | GPT-6 Luna | High | 11.54 | #108 |
| 13 | MiMo-V2.6-Flash | High | 11.54 | #183 |
No result here: #3 Gemini 4 Neon, #4 GPT-6.2 Astra, #7 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=twinlab-bench-pass-rate · How It Works · Data refreshed daily, snapshot 2026-11-22.