EnterpriseMem-Bench: leaderboard
Metric: Execution accuracy (%; all 1,400 turns of 300 multi-turn Text-to-SQL sessions over BIRD Financial, SEC EDGAR and Northwind; Condition B: two-turn working memory plus resolved context keys; single run). Source: arxiv.org. Saturation forecast: Around April 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 86.4 |
| 2 | GPT-5 Mini | 83.2 |
| 3 | Claude Sonnet 4.5 (Non-reasoning) | 79.8 |
| 4 | Claude Sonnet 4.6 (Non-reasoning) | 59.6 |
| 5 | Claude Opus 4.6 (Non-reasoning) | 58.7 |
Interactive version: theaggregate.ai/benchmark?slug=enterprisemem-bench · How It Works · Data refreshed daily, snapshot 2026-09-26.