MILU — leaderboard
Multilingual knowledge-and-reasoning evaluation reported in Anthropic's Claude Opus 4.8 system card.
Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 93.6 |
| 2 | Claude Mythos 5 | 92.9 |
| 3 | Claude Mythos Preview | 92.7 |
| 4 | Claude Opus 4.8 | 91.1 |
| 5 | GPT-5.4 | 90.6 |
| 6 | Claude Opus 4.7 | 89.9 |
| 7 | Claude Sonnet 4.6 | 89.4 |
| 8 | Claude Sonnet 5 | 89.3 |
Interactive version: theaggregate.ai/benchmark?slug=milu · How the rankings work · Data refreshed daily, snapshot 2026-07-22.