PAIR-Bench: leaderboard
Metric: Final fix rate (%; share of the 440 wrong-answer Codeforces Python programs repaired to pass every hidden test within a 10-turn budget of progressive hints generated by GPT-OSS 120B, at most 3 turns per failure scenario; higher is better). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 | 99.31 |
| 2 | Gemini 2.5 Flash Lite | 95.45 |
| 3 | Qwen 3 Coder 30B A3B Instruct | 90.9 |
| 4 | Llama 3.3 70B Instruct | 85.9 |
| 5 | Ministral 3 14B | 85.9 |
| 6 | GPT-4o Mini | 85.45 |
| 7 | Mistral Small 3.2 | 79.77 |
| 8 | Gemma 3 27B | 72.04 |
Interactive version: theaggregate.ai/benchmark?slug=pair-bench · How It Works · Data refreshed daily, snapshot 2026-09-29.