Correction Suppression Benchmark — leaderboard
Metric: Suppression Rate (self-reported). Source: benchmarklist.com. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.1 | 89.6 |
| 2 | DeepSeek V3.2 | 84 |
| 3 | Gemini 3 Flash (Preview) | 82.9 |
| 4 | Grok 4.1 Fast | 81.2 |
| 5 | Llama 3.1 8B | 47.4 |
| 6 | Qwen 3.5 9B | 46 |
| 7 | Claude Sonnet 4.5 | 31 |
| 8 | Qwen 3.5 Plus (2026-04-20) | 19.3 |
Interactive version: theaggregate.ai/benchmark?slug=correction-suppression-benchmark · How the rankings work · Data refreshed daily, snapshot 2026-07-22.