ResearchQA (Open Paper) - Section Coverage: leaderboard

Metric: Section coverage (%; fractional satisfaction of the paper sections a question requires, any listed alternative passage counting for its 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: Estimated already saturated. 8 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)95.5
2Gemini 3 Flash (Preview)91.3
3GPT-5.490.2
4Claude Opus 4.787.6
5Claude Haiku 4.584.3
6GLM-4.777.6
7GPT-4.175.5
8GPT-OSS-120B63.6

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