PRDBench - DEBUG: leaderboard

The second PRDBench round: after the judge agent's feedback on its first attempt, each model's minimal agent revises its 50 projects and the judge re-runs the test plans; the score is the average pass rate. It measures repair from feedback, where the headline board measures building from scratch.

Metric: Average pass rate (%). Source: github.com. Saturation forecast: Around February 2027. 8 models tracked. Updated 17 Nov 2026.

Top models

#ModelScoreOverall rank
1GPT-5.269#185
2Claude Sonnet 4.556.4#258
3Qwen 3 Coder 480B A35B Instruct48.29#653
4Kimi K2 090536.17#564
5GLM-4.735.33#379
6Gemini 3 Pro27.28#145
7DeepSeek V3.224.8#417
8MiniMax-M224.75#687

No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.

Interactive version: theaggregate.ai/benchmark?slug=prdbench-debug · How It Works · Data refreshed daily, snapshot 2026-11-17.