MMLU Pro leaderboard
- Claude Fable 5.1 leads
- 92.4%
- models measured
- 92
- lead over #2
- +0.8 pts
- median
- 86.0%
Leader on MMLU Pro · read October 21
On October 21, 2026, 92 of our catalog's models had a MMLU Pro result, and Anthropic Claude Fable 5.1 led with 92.4%.
MMLU Pro is over 12,000 multiple-choice questions across 14 subjects, from law and history to physics, each with ten options instead of four. The number is the share answered correctly, as run by Vals AI.
Role in the index
Limit: The top of the board is close together: when we read it on October 15, 2026, the five leading models all scored above 90%.
We collect this benchmark and show it as supporting evidence. It is not part of the Vibe Coding Index, because it measures something other than coding and the index is about coding. Read the methodology
| # | Model | Result | Latency, as printed | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1Anthropic | 92.4% | 21 s | 89.1 | $50.00 | |
| 2 | Claude Opus 5Anthropic | 91.6% | 9.6 s | 81.8 | $25.00 | |
| 3 | Claude Fable 5Anthropic | 91.5% | 25 s | 82.1 | $50.00 | |
| 4 | Gemini 3.1 Pro PreviewGoogle | 91.0% | 24 s | 35.3 | $12.00 | |
| 5 | Gemini 3.8 FlashGoogle | 90.2% | 7.8 s | 70.5 | $4.125 | |
| 6 | Gemini 3.7 FlashGoogle | 90.1% | 4.2 s | 69.9 | $3.75 | |
| 7 | Claude Opus 4.7Anthropic | 89.9% | 3m 08s | 51.1 | $25.00 | |
| 8 | Claude Opus 4.8Anthropic | 89.6% | 23 s | 66.0 | $25.00 | |
| 9 | Gemini 3.5 FlashGoogle | 89.5% | 26 s | 42.8 | $9.00 | |
| 10 | Grok 4.6xAI | 89.4% | 55 s | 76.4 | $6.00 |
Only models in our catalog are listed, and each appears once with its best published run. 92 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out. Every other column is a figure the board publishes for the same run.
Cheapest good model on MMLU Pro · Best open-weight model on MMLU Pro