DARE-bench (Data Science) - Time-Series Forecasting (Exogenous Features): leaderboard
Metric: Clipped R-squared (0 to 1, shown times 100) on the 57 forecasting tasks whose test inputs keep the exogenous features; 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: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3.7 Sonnet | 49.88 | #241 |
| 2 | O4 Mini | 42.29 | #172 |
| 3 | GPT-4.1 | 40.78 | #240 |
| 4 | GPT-5 | 36.83 | #91 |
| 5 | GPT-4o | 35.54 | #333 |
| 6 | Qwen 3 32B | 26.96 | #424 |
| 7 | Qwen 3 4B | 6.97 | #823 |
| 8 | Claude Sonnet 4 | 4.8 | #194 |
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-time-series-forecasting-exogenous-features · How It Works · Data refreshed daily, snapshot 2026-10-11.