DataClawEval - MySQL: leaderboard

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 20 MySQL 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

#ModelScore
1CodeBuddy + GPT 5.588.8
2CodeBuddy + Gemini 3.5 Flash85.2
3CodeBuddy + Claude Opus 4.885.1
4CodeBuddy + Claude Sonnet 584.2
5CodeBuddy + DeepSeek V4 Pro83.7
6CodeBuddy + Kimi K2.683.6
7CodeBuddy + GLM 5.283
8CodeBuddy + Hy381.9
9CodeBuddy + MiniMax M381.6
10CodeBuddy + GPT 5.3 Codex81.6

Interactive version: theaggregate.ai/benchmark?slug=dataclaweval-mysql · How It Works · Data refreshed daily, snapshot 2026-09-29.