MMLU-Pro leaderboard: who is #1

Name: MMLU-Pro rankings
Creator: TIGER-Lab
License: https://creativecommons.org/licenses/by/4.0/

TIGER-Lab · Accuracy, higher is better · 100 models · stale since Mar 11, 2026, not counted

Top 25 of 100 models, best variant per model as published

#	Model	Score
1	Gemini 3.1 Pro Previewas “Gemini-3.1-Pro”	91.2%
2	Gemini 3 Proas “Gemini-3-Pro(11/25)”	90.1%
3	o1as “GPT-o1”	89.3%
4	Claude Opus 4.6as “Claude-4.6-Opus(Thinking)”	89.1%
5	Gemini 3 Flashas “Gemini-3-Flash(12/25)”	88.6%
6	MiniMax M2.1as “MiniMax-M2.1”	88.0%
7	Qwen3.5 397B A17Bas “Qwen3.5-397B-A17B”	87.8%
8	Seed2.0 Liteas “Seed2.0-Lite”	87.7%
9	GPT-5.4OpenAI	87.5%
10	Claude Sonnet 4.5as “Claude-4.5-Sonnet(Thinking)”	87.4%
10	GPT-5.2OpenAI	87.4%
12	Claude Opus 4as “Claude-4-Opus-Thinking”	87.3%
12	Claude Opus 4.5as “Claude-4.5-Opus(Thinking)”	87.3%
12	Claude Sonnet 4.6as “Claude-4.6-Sonnet(Thinking)”	87.3%
15	Hunyuan T1as “Hunyuan-T1”	87.2%
16	GPT-5as “GPT-5(high)”	87.1%
16	K2.5 1t A32Bas “K2.5-1T-A32B”	87.1%
18	Grok 4as “Grok-4”	87.0%
18	Seed V1.5as “Seed-Thinking-v1.5”	87.0%
18	Seed2.0 Proas “Seed2.0-Pro”	87.0%
21	Qwen3.5 122B A10Bas “Qwen3.5-122B-A10B”	86.7%
22	Seed1.6as “Seed1.6-Thinking”	86.6%
22	Seed1.6 Baseas “Seed1.6-Base”	86.6%
24	GPT-5.1OpenAI	86.4%
24	Seed1.6 Adaas “Seed1.6-Ada-Thinking”	86.4%