MILU: leaderboard
Multilingual knowledge-and-reasoning evaluation reported in Anthropic's Claude Opus 4.8 system card.
Metric: Score (system card). Source: anthropic.com. Source: benchmarklist.com. Saturation forecast: Around July 2028. 15 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 93.6 | #58 |
| 2 | Claude Opus 5.5 (Max) | 93.1 | #3 (Claude Opus 5.5) |
| 3 | Claude Fable 5.1 (Max) | 93 | #9 (Claude Fable 5.1) |
| 4 | Claude Fable 5 (Max) | 92.9 | #16 (Claude Fable 5) |
| 5 | Claude Mythos 5 | 92.9 | #2 |
| 6 | Claude Mythos Preview | 92.7 | #4 |
| 7 | Claude Opus 5 | 92.1 | #12 |
| 8 | Claude Opus 5 (Max) | 92.1 | #12 (Claude Opus 5) |
| 9 | Claude Sonnet 5.5 (Max) | 91.6 | #11 (Claude Sonnet 5.5) |
| 10 | Claude Opus 4.8 | 91.1 | #37 |
| 11 | GPT-5.4 | 90.6 | #79 |
| 12 | Claude Opus 4.7 | 89.9 | #49 |
| 13 | Claude Sonnet 4.6 | 89.4 | #90 |
| 14 | Claude Sonnet 5 | 89.3 | #57 |
| 15 | Claude Sonnet 5 (Max) | 89.3 | #57 (Claude Sonnet 5) |
No result here: #6 GPT-6 Astra, #7 GPT-6.1 Sol, #8 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=milu · How It Works · Data refreshed daily, snapshot 2026-10-20.