DataClawEval - English Tasks: leaderboard
DataClawEval gives agents industrial data-engineering tasks rebuilt from production workflows: they must inspect the data, write and debug a job, and materialize correct output tables. This board covers the English-language half of the tasks. Grading is deterministic, comparing the produced artifact row by row against live databases and adding a process score for exploration, execution efficiency and self-verification.
Metric: Rule-based task score (%; per task a weighted sum, usually 0.7 and 0.3, of the artifact score, checked row by row against live databases by task-specific deterministic scripts, and the process score for exploration, execution efficiency and self-verification, mean over the 50 English-language tasks; one run per task, every model in the same Tencent CodeBuddy agent scaffold). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | CodeBuddy + GPT 5.5 | 76.9 | |
| 2 | CodeBuddy + GLM 5.1 | 76.5 | |
| 3 | CodeBuddy + DeepSeek V4 Flash | 76.2 | |
| 4 | CodeBuddy + Gemini 3.1 Pro | 75.3 | |
| 5 | CodeBuddy + Claude Opus 4.8 | 75.1 | |
| 6 | CodeBuddy + Gemini 3.5 Flash | 74.3 | |
| 7 | CodeBuddy + MiniMax M3 | 74.3 | |
| 8 | CodeBuddy + DeepSeek V4 Pro | 74.3 | |
| 9 | CodeBuddy + Claude Sonnet 5 | 73.5 | |
| 10 | CodeBuddy + GLM 5.2 | 71.8 |
Interactive version: theaggregate.ai/benchmark?slug=dataclaweval-english-tasks · How It Works · Data refreshed daily, snapshot 2026-11-13.