ActiveSciBench-Chem (LLM-AutoSciLab): leaderboard
Metric: Symbolic accuracy (%; share of the 57 enzyme-kinetics tasks whose recovered rate law an LLM judge rates equivalent to the hidden law up to fitted constants; budget-limited active experiments driven by the LLM-AutoSciLab framework with this backbone). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4o Mini | 35.09 |
| 2 | Qwen 3 32B | 25.56 |
| 3 | Qwen 3 14B | 23.88 |
| 4 | Qwen 3 4B | 12.92 |
Interactive version: theaggregate.ai/benchmark?slug=activescibench-chem-llm-autoscilab · How It Works · Data refreshed daily, snapshot 2026-09-26.