CoCoReviewBench - Verifiability: leaderboard

CoCoReviewBench (2026) evaluates AI peer reviewers on ICLR and NeurIPS papers against category-specific human review opinions that were filtered for correctness using reviewer, author and meta-review discussions. This board measures whether the claims can be checked from their reasoning or references on a 1 to 5 judge scale, shown as the difference from the leave-one-out human reviewers, so positive values beat the humans; higher is better.

Metric: Category-level verifiability score (whether a claim can be checked from its reasoning, common knowledge or references) on the 1-5 judge scale, printed as the difference from the human reference reviews (2.38, leave-one-out: one human review scored against the others), so a positive value is better than the human reviewers and the range is -1.38 to +2.62; AI reviews of 1,300 ICLR and NeurIPS papers sampled from CoCoReviewBench (100 per year, original score distribution kept), each split into atomic opinions and compared category by category with the filtered human opinions by a GPT-5-Mini judge at temperature 0, general models prompted with the AI Scientist review prompt at temperature 0.6; higher is better. Source: arxiv.org. Saturation forecast: Around March 2027. 17 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1GPT-5.20.78#190
2GPT-5 Mini0.53#373
3DeepReviewer-14B0.41#852
4Gemini 3 Pro0.34#146
5DeepReviewer-7B0.3
6Gemini 3 Flash0.14#180
7QwQ-32B0.02#913
8Qwen 3 32BThinking-0.15#983
9nemotron-3-nano-30B-a3BReasoning-0.29#1902
10OpenReviewer-8B-0.31
11Qwen 3 8BThinking-0.45#1890
12CycleReviewer-8B-0.48
13CycleReviewer-70B-0.48#1899
14Qwen 2.5 7B-0.59#2902
15Llama 3.1 8B-0.66#5193

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=cocoreviewbench-verifiability · How It Works · Data refreshed daily, snapshot 2026-11-22.