SurveyReview: leaderboard
Metric: Mean squared error of predicted review scores, averaged over readability, criticalness, comprehensiveness and structure (0 to 16, lower is better; zero-shot LLM-as-a-judge with the unified dimension-specific rubric prompt on the full survey text, against scores annotated from real peer-review reports of the test-split surveys (MOPRD, F1000Research, OpenReview) on the {-2, -1, +1, +2} scale). Source: arxiv.org. Saturation forecast: Around December 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.2 | 2.28 |
| 2 | Claude Opus 4.5 (Thinking) | 2.77 |
| 3 | Qwen 3 32B | 3.21 |
| 4 | GLM-4.7 | 3.62 |
| 5 | Gemini 3 Pro (Preview) | 3.94 |
| 6 | DeepSeek V3.2 | 3.97 |
Interactive version: theaggregate.ai/benchmark?slug=surveyreview · How It Works · Data refreshed daily, snapshot 2026-09-26.