BenchBench-Protocol - Microbiology and Microbial Methods: leaderboard
Metric: Normalized rubric score (%; weighted rubric elements met by the response to real protocol-modification tasks in the microbiology and microbial methods domain (14 tasks), graded by GPT-5.6 Terra; mean of repeated attempts per task). Source: arxiv.org. Saturation forecast: Around November 2027. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5 (Max) | 58.3 |
| 2 | GPT-5.6 Sol (Max) | 47.9 |
| 3 | Kimi K3 (Max) | 46.3 |
| 4 | GPT-5.6 Terra (Max) | 43.9 |
| 5 | GPT-5.6 Luna (Max) | 41.4 |
| 6 | Grok 4.5 (High) | 37.6 |
| 7 | Inkling (Max) | 37.1 |
| 8 | Gemini 3.6 Flash (High) | 31 |
| 9 | GLM-5.2 (Max) | 29.3 |
Interactive version: theaggregate.ai/benchmark?slug=benchbench-protocol-microbiology-and-microbial-methods · How It Works · Data refreshed daily, snapshot 2026-09-26.