ResearchQA (Open Paper) - Citation Precision: leaderboard

Metric: Citation precision (%; share of cited passages that match an alternative in a required section, citation-grounded answers from the Open Paper chat-with-paper harness to a 100-row evenly spaced sample of 6,211 single-paper questions over 494 open-access papers, citations checked by a normalizing substring matcher against the extracted paper text; higher is better). Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.

Top models

#ModelScore
1GPT-4.177.6
2GLM-4.774.4
3Gemini 3.1 Pro (Preview)72.3
4Claude Haiku 4.571.6
5GPT-OSS-120B66
6GPT-5.464.7
7Claude Opus 4.756.9
8Gemini 3 Flash (Preview)49.1

Interactive version: theaggregate.ai/benchmark?slug=researchqa-open-paper-citation-precision · How It Works · Data refreshed daily, snapshot 2026-09-29.