ResearchQA (Open Paper) - Citation Accuracy: leaderboard
Metric: Citation accuracy (%; share of cited passages that are verifiable substrings of the paper, 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 December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Haiku 4.5 | 84.5 |
| 2 | GLM-4.7 | 84 |
| 3 | Gemini 3 Flash (Preview) | 83.5 |
| 4 | GPT-5.4 | 83.4 |
| 5 | Gemini 3.1 Pro (Preview) | 81.7 |
| 6 | Claude Opus 4.7 | 80.9 |
| 7 | GPT-4.1 | 78.6 |
| 8 | GPT-OSS-120B | 70 |
Interactive version: theaggregate.ai/benchmark?slug=researchqa-open-paper-citation-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-29.