DARE-bench (Data Science) - Regression (Instruction Following): leaderboard
Metric: Strict accuracy (%) on the 45 regression instruction-following tasks: the agent must reproduce a reference workflow exactly and scores 1 only when its predictions equal the reference solution's; DARE-bench test tasks derived from recently updated Kaggle datasets; the model works as a data-science agent with a sandboxed Python execution tool (5 interaction turns, 200 s per execution, greedy decoding), mean of three repeats; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 57.24 | #91 |
| 2 | O4 Mini | 53.62 | #172 |
| 3 | GPT-4.1 | 52.17 | #240 |
| 4 | Claude 3.7 Sonnet | 46.37 | #241 |
| 5 | GPT-4o | 20.28 | #333 |
| 6 | Qwen 3 32B | 15.21 | #424 |
| 7 | Claude Sonnet 4 | 15.21 | #194 |
| 8 | Qwen 3 4B | 0.72 | #823 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=dare-bench-data-science-regression-instruction-following · How It Works · Data refreshed daily, snapshot 2026-10-11.