Review Error Injection (OpenAIReview): leaderboard
Metric: Error detection recall (%; share of injected errors that the review's comments quote and correctly explain, fuzzy quote match then a Gemini-3 Flash Preview explanation judge) on the 24-paper frontier subset of a perturbation benchmark built from 74 clean arXiv papers in 8 subject classes, with surface (math-token) and claim, reasoning and experimental errors injected; backends via OpenRouter without reasoning mode; the OpenAIReview agentic review system (passage-level review with a validate-and-dedupe pipeline) backed by each model; higher is better. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | OpenAIReview + GPT-5.5 (Non-reasoning) | 71.6 |
| 2 | OpenAIReview + Claude-Opus-4.7 | 68.1 |
| 3 | OpenAIReview + DeepSeek-V4-Flash (Non-reasoning) | 55.8 |
| 4 | OpenAIReview + Grok-4.1-Fast (Non-reasoning) | 52.6 |
| 5 | OpenAIReview + Qwen3.6-35B-A3B (Non-reasoning) | 45.4 |
| 6 | OpenAIReview + Gemini-3.1-Flash-Lite (Non-reasoning) | 33 |
Interactive version: theaggregate.ai/benchmark?slug=review-error-injection-openaireview · How It Works · Data refreshed daily, snapshot 2026-09-29.