EntLORE - Explicit Lookup (Agentic Retrieval): leaderboard
EntLORE (2026) builds an anonymized enterprise world of 2,341 routine documents from an audited truth graph. This board is answer accuracy in percent on its explicit-lookup questions (L1), whose answer is stated in one document, answered through an agent that searches and reads a dense index of the released corpus over at most 30 iterations. Higher is better.
Metric: Answer accuracy (%; L1, 469 questions answered by a stated fact; agentic retrieval: search and fetch tools over a dense index of the released corpus, at most 30 LLM iterations; 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: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.6 (Thinking) | 54.7 | #161 (Claude Sonnet 4.6) |
| 2 | GLM-5.2 | 51 | #138 |
| 3 | DeepSeek V4 Flash (Reasoning) | 49.6 | #258 (DeepSeek V4 Flash) |
| 4 | GPT-5.4 | 49.1 | #123 |
| 5 | DeepSeek V4 Pro (Reasoning) | 48.4 | #188 (DeepSeek V4 Pro) |
| 6 | Kimi K2.6 | 46.5 | #178 |
| 7 | Qwen 3.5 397B A17B | 46 | #246 |
| 8 | GPT-5.4 Mini | 42.5 | #389 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=entlore-explicit-lookup-agentic-retrieval · How It Works · Data refreshed daily, snapshot 2026-11-13.