EUDAIMONIA: leaderboard

Metric: Violation rate (%) over 3,147 design-code checks, Claude Opus 4.6 judge. Source: eudaimonia-bench.github.io. Saturation forecast: Around 2029. 22 models tracked.

Top models

#ModelScore
1GPT-5.527.2
2Claude Opus 4.730.7
3Claude Opus 4.630.8
4GPT-5.434.5
5Grok 4.337.6
6GPT-4o39.9
7GPT-4o Mini43.8
8Gemini 3 Flash54.7
9Qwen 3 32B54.9
10Qwen 3.6 Max Preview55.6
11Qwen 3 14B57
12Qwen 3 8B57.1
13Claude Sonnet 457.2
14Gemini 3.1 Pro (Preview)57.7
15DeepSeek V4 Pro (Reasoning)57.7

Interactive version: theaggregate.ai/benchmark?slug=eudaimonia · How It Works · Data refreshed daily, snapshot 2026-09-25.