LitReviewBench - Paper Structure: leaderboard

Metric: Expert-preference rating (Elo scale, Bradley-Terry aggregation of about 3,000 anonymized pairwise battles judged by matched domain experts on D3 organization of prior work; literature review drafts on AI topics; the human-draft baseline is in the rating pool). Source: arxiv.org. Saturation forecast: Around March 2027. 9 models tracked.

Top models

#ModelScore
1Sonar Deep Research1262.1
2Claude Opus 4.51177.6
3Qwen 3 235B A22B886
4Grok 4780.2
5GLM-4.6564
6Gemini 2.5 Pro526

Interactive version: theaggregate.ai/benchmark?slug=litreviewbench-paper-structure · How It Works · Data refreshed daily, snapshot 2026-09-26.