EntSQL - With Evidence: leaderboard

Metric: Execution accuracy (%) with concise expert-curated evidence snippets instead of the full document; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.617.6
2GLM-5.117.1
3GPT-5.416.7
4Qwen 3.6 Max Preview16.3
5Claude Opus 4.615.5
6Gemini 3.1 Pro (Preview)12.8
7Kimi K2.610.6

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