Beyond Rating - Strength Recall: leaderboard
Beyond Rating (2026) evaluates AI peer reviewers on the text of their reviews: generated reviews of ICLR and NeurIPS papers are split into atomic points and matched by Qwen3-235B against filtered high-confidence human reviews. This board is strength Max-Recall in percent, the share of one human reviewer's strength points the generated review covers, taking the best-covered reviewer per paper; higher is better.
Metric: Strength Max-Recall (from 0-1, times 100): share of a single human reviewer's strength points that the generated review's strength points cover, taking the best-covered reviewer per paper, on 1,000 test papers from ICLR 2024-2026 and NeurIPS 2022-2025 with three to five high-confidence human reviews each, the model writing a full review from the parsed paper; review points are split into atomic claims and matched to the human reviews' claims by Qwen3-235B; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepReviewer-14B | 61 | #844 |
| 2 | Qwen 3 30B A3B 2507 Instruct | 53 | #1100 |
| 3 | Qwen 3 235B A22B 2507 Instruct | 53 | #616 |
| 4 | DeepSeek V3.2 | 51 | #419 |
| 5 | Claude Sonnet 4.5 | 48 | #261 |
| 6 | SEA-E-7B | 47 | |
| 7 | Qwen 3 8B | 46 | #1873 |
| 8 | AgentReview + GPT-5 | 45 | |
| 9 | Gemini 3 Pro (Preview) | 42 | #119 |
| 10 | AI Scientist + GPT-5 | 42 | |
| 11 | Llama 3.1 8B Instruct | 39 | #4600 |
| 12 | Llama 3.1 70B Instruct | 39 | #1571 |
| 13 | GPT-5.2 | 38 | #185 |
| 14 | OpenReviewer-8B | 37 | |
| 15 | CycleReviewer-70B | 30 | #1880 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=beyond-rating-strength-recall · How It Works · Data refreshed daily, snapshot 2026-11-21.