Deep-Research Citation Benchmark - Factual Support: leaderboard

Metric: Cohen kappa (-1 to 1) between the LLM judge and human-reviewed gold labels on the factual support rubric criterion of 624 attribution-citation pairs parsed from an adversarial 25-domain deep-research report (scores binarized at 0.5); higher is better. Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.

Top models

#ModelScore
1Claude Opus 4.60.7
2Claude Sonnet 4.60.68
3Gemini 3.1 Flash Lite (Preview)0.65
4GPT-5 Mini0.65
5Claude Haiku 4.50.63
6Gemini 3.1 Pro (Preview)0.62
7GPT-OSS-120B0.59
8GPT-5.4 Mini0.58

Interactive version: theaggregate.ai/benchmark?slug=deep-research-citation-benchmark-factual-support · How It Works · Data refreshed daily, snapshot 2026-09-29.