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
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 | 27.2 |
| 2 | Claude Opus 4.7 | 30.7 |
| 3 | Claude Opus 4.6 | 30.8 |
| 4 | GPT-5.4 | 34.5 |
| 5 | Grok 4.3 | 37.6 |
| 6 | GPT-4o | 39.9 |
| 7 | GPT-4o Mini | 43.8 |
| 8 | Gemini 3 Flash | 54.7 |
| 9 | Qwen 3 32B | 54.9 |
| 10 | Qwen 3.6 Max Preview | 55.6 |
| 11 | Qwen 3 14B | 57 |
| 12 | Qwen 3 8B | 57.1 |
| 13 | Claude Sonnet 4 | 57.2 |
| 14 | Gemini 3.1 Pro (Preview) | 57.7 |
| 15 | DeepSeek V4 Pro (Reasoning) | 57.7 |
Interactive version: theaggregate.ai/benchmark?slug=eudaimonia · How It Works · Data refreshed daily, snapshot 2026-09-25.