Share promptsSign inExplore benchmarks
← Reasoning & knowledge benchmarks

MMLU Pro leaderboard (Sep 2026): AI model scores

As of 1 Sep 2026, the highest reported Meta score on MMLU Pro is Muse Spark 1.1 (Meta) at 88.73%, #17 on that leaderboard, per Vals AI. The source no longer updates this leaderboard.

What it measures

Academic multiple-choice questions covering 14 subjects, including STEM, humanities and social sciences.

Harder, 10-option version of the classic MMLU knowledge test across 14 subjects.

What the score means

Accuracy

Share of questions answered correctly.

Results from published AI leaderboards. Compare models within each benchmark; scores from different tests aren’t directly comparable. How we collect these results

Scores by model

Run by Vals AI. Leaderboard dated 1 Sep 2026 (no longer updated by the source). Last checked 22 Oct 2026. Showing top 25 of 138 models listed.

Highlight a provider: Anthropic OpenAI Google xAI Meta Alibaba Moonshot

Highlighting Meta models. Other providers are dimmed. Show all providers

  • Anthropic
  • OpenAI
  • Google
  • xAI
  • Meta
  • Alibaba
  • Moonshot
MMLU Pro: top 15 by AccuracyBars from zero. Leader: Claude Fable 5.1 at 92.38%. Meta models highlighted. Full values in the table below.0%20%40%60%80%100%Claude Fable 5.1 (Anthropic), rank 1: 92.38%AClaude Fable 5.192.38%Claude Opus 5 (Anthropic), rank 2: 91.59%AClaude Opus 591.59%Claude Fable 5 (Anthropic), rank 3: 91.50%AClaude Fable 591.50%Gemini 3.1 Pro Preview (02/26) (Google), rank 4: 90.99%GGemini 3.1 Pro Preview90.99%Gemini 3.8 Flash (Google), rank 5: 90.22%GGemini 3.8 Flash90.22%Gemini 3.7 Flash (Google), rank 6: 90.12%GGemini 3.7 Flash90.12%Gemini 3 Pro (11/25) (Google), rank 7: 90.10%GGemini 3 Pro90.10%Claude Opus 4.7 (Anthropic), rank 8: 89.87%AClaude Opus 4.789.87%Claude Opus 4.8 (Anthropic), rank 9: 89.58%AClaude Opus 4.889.58%Gemini 3.5 Flash (Google), rank 10: 89.52%GGemini 3.5 Flash89.52%Grok 4.6 (xAI), rank 11: 89.40%XGrok 4.689.40%Qwen 3.7 Max (Alibaba), rank 12: 89.31%QQwen 3.7 Max89.31%Gemini 3.6 Flash (Google), rank 13: 89.28%GGemini 3.6 Flash89.28%Grok 4.5 (xAI), rank 14: 89.22%XGrok 4.589.22%Claude Opus 4.6 (Thinking) (Anthropic), rank 15: 89.11%AClaude Opus 4.689.11%Muse Spark 1.1 (Meta), rank 17: 88.73%M#17 Muse Spark 1.188.73%Muse Spark 1.2 (Meta), rank 20: 88.28%M#20 Muse Spark 1.288.28%
MMLU Pro: top 12 by AccuracyBars from zero. Leader: Claude Fable 5.1 at 92.38%. Meta models highlighted. Full values in the table below.0%50%100%Claude Fable 5.1 (Anthropic), rank 1: 92.38%AClaude Fable 5.192.38%Claude Opus 5 (Anthropic), rank 2: 91.59%AClaude Opus 591.59%Claude Fable 5 (Anthropic), rank 3: 91.50%AClaude Fable 591.50%Gemini 3.1 Pro Preview (02/26) (Google), rank 4: 90.99%GGemini 3.1 Pro P…90.99%Gemini 3.8 Flash (Google), rank 5: 90.22%GGemini 3.8 Flash90.22%Gemini 3.7 Flash (Google), rank 6: 90.12%GGemini 3.7 Flash90.12%Gemini 3 Pro (11/25) (Google), rank 7: 90.10%GGemini 3 Pro90.10%Claude Opus 4.7 (Anthropic), rank 8: 89.87%AClaude Opus 4.789.87%Claude Opus 4.8 (Anthropic), rank 9: 89.58%AClaude Opus 4.889.58%Gemini 3.5 Flash (Google), rank 10: 89.52%GGemini 3.5 Flash89.52%Grok 4.6 (xAI), rank 11: 89.40%XGrok 4.689.40%Qwen 3.7 Max (Alibaba), rank 12: 89.31%QQwen 3.7 Max89.31%Muse Spark 1.1 (Meta), rank 17: 88.73%M#17 Muse Spark 1…88.73%Muse Spark 1.2 (Meta), rank 20: 88.28%M#20 Muse Spark 1…88.28%
MMLU Pro: top 15 by AccuracyDot plot, axis starting at 82.5% (not zero). Leader: Claude Fable 5.1 at 92.38%. Meta models highlighted. Full values in the table below.82.5%85%87.5%90%92.5%ACCURACY · AXIS STARTS AT 82.5%, NOT ZEROClaude Fable 5.1 (Anthropic), rank 1: 92.38%AClaude Fable 5.192.38%Claude Opus 5 (Anthropic), rank 2: 91.59%AClaude Opus 591.59%Claude Fable 5 (Anthropic), rank 3: 91.50%AClaude Fable 591.50%Gemini 3.1 Pro Preview (02/26) (Google), rank 4: 90.99%GGemini 3.1 Pro Preview90.99%Gemini 3.8 Flash (Google), rank 5: 90.22%GGemini 3.8 Flash90.22%Gemini 3.7 Flash (Google), rank 6: 90.12%GGemini 3.7 Flash90.12%Gemini 3 Pro (11/25) (Google), rank 7: 90.10%GGemini 3 Pro90.10%Claude Opus 4.7 (Anthropic), rank 8: 89.87%AClaude Opus 4.789.87%Claude Opus 4.8 (Anthropic), rank 9: 89.58%AClaude Opus 4.889.58%Gemini 3.5 Flash (Google), rank 10: 89.52%GGemini 3.5 Flash89.52%Grok 4.6 (xAI), rank 11: 89.40%XGrok 4.689.40%Qwen 3.7 Max (Alibaba), rank 12: 89.31%QQwen 3.7 Max89.31%Gemini 3.6 Flash (Google), rank 13: 89.28%GGemini 3.6 Flash89.28%Grok 4.5 (xAI), rank 14: 89.22%XGrok 4.589.22%Claude Opus 4.6 (Thinking) (Anthropic), rank 15: 89.11%AClaude Opus 4.689.11%Muse Spark 1.1 (Meta), rank 17: 88.73%M#17 Muse Spark 1.188.73%Muse Spark 1.2 (Meta), rank 20: 88.28%M#20 Muse Spark 1.288.28%
MMLU Pro: top 12 by AccuracyDot plot, axis starting at 80% (not zero). Leader: Claude Fable 5.1 at 92.38%. Meta models highlighted. Full values in the table below.80%85%90%AXIS STARTS AT 80%, NOT ZEROClaude Fable 5.1 (Anthropic), rank 1: 92.38%AClaude Fable 5.192.38%Claude Opus 5 (Anthropic), rank 2: 91.59%AClaude Opus 591.59%Claude Fable 5 (Anthropic), rank 3: 91.50%AClaude Fable 591.50%Gemini 3.1 Pro Preview (02/26) (Google), rank 4: 90.99%GGemini 3.1 Pro P…90.99%Gemini 3.8 Flash (Google), rank 5: 90.22%GGemini 3.8 Flash90.22%Gemini 3.7 Flash (Google), rank 6: 90.12%GGemini 3.7 Flash90.12%Gemini 3 Pro (11/25) (Google), rank 7: 90.10%GGemini 3 Pro90.10%Claude Opus 4.7 (Anthropic), rank 8: 89.87%AClaude Opus 4.789.87%Claude Opus 4.8 (Anthropic), rank 9: 89.58%AClaude Opus 4.889.58%Gemini 3.5 Flash (Google), rank 10: 89.52%GGemini 3.5 Flash89.52%Grok 4.6 (xAI), rank 11: 89.40%XGrok 4.689.40%Qwen 3.7 Max (Alibaba), rank 12: 89.31%QQwen 3.7 Max89.31%Muse Spark 1.1 (Meta), rank 17: 88.73%M#17 Muse Spark 1…88.73%Muse Spark 1.2 (Meta), rank 20: 88.28%M#20 Muse Spark 1…88.28%
Accuracy
Share of questions answered correctly.

All scores

MMLU Pro scores, Meta models highlighted
RankModelProviderAccuracyPrice in / out ($/1M tokens)
1 Claude Fable 5.1Anthropic92.38%$10 / $50
2 Claude Opus 5Anthropic91.59%$5 / $25
3 Claude Fable 5Anthropic91.50%$10 / $50
4 Gemini 3.1 Pro Preview (02/26)Google90.99%$2 / $12
5 Gemini 3.8 FlashGoogle90.22%$1.5 / $7.5
6 Gemini 3.7 FlashGoogle90.12%$1.5 / $7.5
7 Gemini 3 Pro (11/25)Google90.10%$2 / $12
8 Claude Opus 4.7Anthropic89.87%$5 / $25
9 Claude Opus 4.8Anthropic89.58%$5 / $25
10 Gemini 3.5 FlashGoogle89.52%$1.5 / $9
Show 15 more rows
RankModelProviderAccuracyPrice in / out ($/1M tokens)
11 Grok 4.6xAI89.40%$2 / $6
12 Qwen 3.7 MaxAlibaba89.31%$2.5 / $7.5
13 Gemini 3.6 FlashGoogle89.28%$1.5 / $7.5
14 Grok 4.5xAI89.22%$2 / $6
15 Claude Opus 4.6 (Thinking)Anthropic89.11%$5 / $25
16 GPT-5.6 SolOpenAI89.10%$4 / $20
17 Muse Spark 1.1Meta88.73%$1.25 / $4.25
18 Qwen 3.8 MaxAlibaba88.60%$2 / $6
19 Gemini 3 Flash (12/25)Google88.59%$0.5 / $3
20 Muse Spark 1.2Meta88.28%$1.25 / $4.25
21 GPT 5.5OpenAI88.14%$5 / $30
22 Kimi K3Moonshot87.97%$3 / $15
23 Claude Opus 4.1 (Thinking)Anthropic87.92%$15 / $75
24 Qwen 3.6 PlusAlibaba87.67%$0.5 / $3
25 Kimi K2.6Moonshot87.57%$0.95 / $4

Source: Vals AI leaderboard ↗

Best-ranked Meta model here: Muse Spark 1.1 (Meta). Try prompts for Muse →