EntLORE - Explicit Lookup (GraphRAG): leaderboard
Metric: Answer accuracy (%; L1, 469 questions answered by a stated fact; 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 December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.2 | 68.5 |
| 2 | DeepSeek V4 Flash (Reasoning) | 67.6 |
| 3 | DeepSeek V4 Pro (Reasoning) | 66.2 |
| 4 | Claude Sonnet 4.6 (Thinking) | 65.8 |
| 5 | Qwen 3.5 397B A17B | 65.6 |
| 6 | Kimi K2.6 | 63.4 |
| 7 | GPT-5.4 | 56.7 |
| 8 | GPT-5.4 Mini | 52.2 |
Interactive version: theaggregate.ai/benchmark?slug=entlore-explicit-lookup-graphrag · How It Works · Data refreshed daily, snapshot 2026-09-29.