DataClawBench: leaderboard
Autonomous data analysis agents are increasingly expected to conduct exploratory analysis with limited human guidance about data. However, existing benchmarks typically evaluate such agents in prior-guided settings, providing selected data sources, explicit data schemas, or cleaned data, thereby understating the exploratory burden. To evaluate this realistic exploratory data analysis task, we intr
Metric: Overall Acc. (self-reported). Source: benchmarklist.com. Saturation forecast: Around July 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.6 | 63.4 | #63 |
| 2 | MiniMax-M2.7 | 41.3 | #258 |
| 3 | Qwen 3.5 Plus | 37.7 | #125 |
| 4 | DeepSeek V3.2 | 34.1 | #205 |
| 5 | GLM-5 | 33.3 | #141 |
| 6 | Kimi K2.5 | 26.3 | #144 |
| 7 | GPT-5.4 | 23.4 | #79 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=dataclawbench · How It Works · Data refreshed daily, snapshot 2026-10-20.