EntLORE - Cross-Source Composition (Agentic Retrieval): leaderboard

Metric: Answer accuracy (%; L2, 204 questions composing facts stated in several sources; 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 June 2028. 8 models tracked.

Top models

#ModelScore
1GPT-5.440.5
2DeepSeek V4 Pro (Reasoning)39.1
3DeepSeek V4 Flash (Reasoning)36.4
4GLM-5.235.9
5Claude Sonnet 4.6 (Thinking)35.6
6Qwen 3.5 397B A17B35
7Kimi K2.631.5
8GPT-5.4 Mini30.4

Interactive version: theaggregate.ai/benchmark?slug=entlore-cross-source-composition-agentic-retrieval · How It Works · Data refreshed daily, snapshot 2026-09-29.