Review Error Injection (OpenAIReview): leaderboard
Detection recall on the injected-error benchmark of Benchmarking Agentic Review Systems (2026) when the OpenAIReview agentic review system, backed by each model, reviews the corrupted papers passage by passage. Percent of injected errors caught and correctly explained on the 24-paper frontier subset; higher is better.
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 | Overall rank |
|---|---|---|---|
| 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 2026-11-13.