ESQ-Bench (Tier 2): leaderboard
Metric: Execution match (%; among executed queries; Tier-2 schemas; over ESQ-Bench's Oracle-first enterprise NL2SQL question bank; execution match among executed queries; schema-linked prompt, temperature 0). Source: arxiv.org. Saturation forecast: Around December 2026. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.6 | 74.9 |
| 2 | GPT-4o | 60.3 |
Interactive version: theaggregate.ai/benchmark?slug=esq-bench-tier-2 · How It Works · Data refreshed daily, snapshot 2026-09-26.