PRDBench: leaderboard

Each model drives the benchmark's minimal coding agent to build 50 Python projects from product requirement documents in one zero-shot round; a fine-tuned judge agent runs each project's test plan and the score is the average pass rate. Unlike unit-test benchmarks such as SWE-bench, the criteria mix unit tests with shell-interaction and file-comparison checks run by an agent judge.

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

Top models

#ModelScoreOverall rank
1Claude Sonnet 4.569.19#258
2GPT-5.262.49#185
3Qwen 3 Coder 480B A35B Instruct43.84#653
4DeepSeek V3.240.11#417
5GLM-4.738.39#379
6Gemini 3 Pro22.76#145
7Kimi K2 090520.52#564
8MiniMax-M217.6#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 · How It Works · Data refreshed daily, snapshot 2026-11-17.