EntSQL - Question Only: leaderboard
Metric: Execution accuracy (%) with only the question and schema (no document); higher is better. Source: arxiv.org. Saturation forecast: Around 2030. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 5.9 |
| 2 | Claude Opus 4.6 | 5.9 |
| 3 | Qwen 3.6 Max Preview | 5.7 |
| 4 | GLM-5.1 | 5.5 |
| 5 | GPT-5.4 | 4.8 |
| 6 | Kimi K2.6 | 4.8 |
| 7 | Gemini 3.1 Pro (Preview) | 4.7 |
Interactive version: theaggregate.ai/benchmark?slug=entsql-question-only · How It Works · Data refreshed daily, snapshot 2026-09-29.