EntLORE - Explicit Lookup (Gold Documents): leaderboard
Metric: Answer accuracy (%; L1, 469 questions answered by a stated fact; gold-document agentic reference: the gold document paths read through the same agent tool loop; 907 questions over 2,341 anonymized enterprise documents; programmatic scoring for entity, set, count and ordered answers, atomic-claim entailment judged by Claude Opus 4.8 for free-form answers). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.2 | 89.2 |
| 2 | GPT-5.4 | 88.9 |
| 3 | Claude Sonnet 4.6 (Thinking) | 88.5 |
| 4 | Kimi K2.6 | 88.2 |
| 5 | GPT-5.4 Mini | 87.5 |
| 6 | DeepSeek V4 Pro (Reasoning) | 86.4 |
| 7 | DeepSeek V4 Flash (Reasoning) | 85.6 |
| 8 | Qwen 3.5 397B A17B | 85.2 |
Interactive version: theaggregate.ai/benchmark?slug=entlore-explicit-lookup-gold-documents · How It Works · Data refreshed daily, snapshot 2026-09-29.