EntLORE - Latent Organizational Reasoning (GraphRAG): 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 latent organizational reasoning questions (L3), whose target relation is stated in no document and must be recovered from routine records, answered through a GraphRAG system that induces an entity graph and community reports from the corpus. Higher is better.
Metric: Answer accuracy (%; L3, 234 questions whose target relation is stated in no document; corpus-induced GraphRAG: an entity graph and community reports induced offline from the released corpus; 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 June 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GLM-5.2 | 43.1 | #138 |
| 2 | DeepSeek V4 Flash (Reasoning) | 39.8 | #258 (DeepSeek V4 Flash) |
| 3 | Qwen 3.5 397B A17B | 39.6 | #246 |
| 4 | DeepSeek V4 Pro (Reasoning) | 38.6 | #188 (DeepSeek V4 Pro) |
| 5 | Claude Sonnet 4.6 (Thinking) | 38.3 | #161 (Claude Sonnet 4.6) |
| 6 | GPT-5.4 | 34.1 | #123 |
| 7 | GPT-5.4 Mini | 28.8 | #389 |
| 8 | Kimi K2.6 | 27.6 | #178 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=entlore-latent-organizational-reasoning-graphrag · How It Works · Data refreshed daily, snapshot 2026-11-13.