MMLU-Pro

1. 1
   Gemini 3.1 Pro Preview

   as “Gemini-3.1-Pro”
   91.2%
2. 2
   Gemini 3 Pro

   as “Gemini-3-Pro(11/25)”
   90.1%
3. 3
   o1

   as “GPT-o1”
   89.3%
4. 4
   Claude Opus 4.6

   as “Claude-4.6-Opus(Thinking)”
   89.1%
5. 5
   Gemini 3 Flash

   as “Gemini-3-Flash(12/25)”
   88.6%
6. 6
   MiniMax M2.1

   as “MiniMax-M2.1”
   88.0%
7. 7
   Qwen3.5 397B A17B

   as “Qwen3.5-397B-A17B”
   87.8%
8. 8
   Seed2.0 Lite

   as “Seed2.0-Lite”
   87.7%
9. 9
   GPT-5.4
   87.5%
10. 10
    Claude Sonnet 4.5

    as “Claude-4.5-Sonnet(Thinking)”
    87.4%
11. 10
    GPT-5.2
    87.4%
12. 12
    Claude Opus 4

    as “Claude-4-Opus-Thinking”
    87.3%
13. 12
    Claude Opus 4.5

    as “Claude-4.5-Opus(Thinking)”
    87.3%
14. 12
    Claude Sonnet 4.6

    as “Claude-4.6-Sonnet(Thinking)”
    87.3%
15. 15
    Hunyuan T1

    as “Hunyuan-T1”
    87.2%
16. 16
    GPT-5

    as “GPT-5(high)”
    87.1%
17. 16
    ?K2.5 1t A32B

    as “K2.5-1T-A32B”
    87.1%
18. 18
    Grok 4

    as “Grok-4”
    87.0%
19. 18
    Seed V1.5

    as “Seed-Thinking-v1.5”
    87.0%
20. 18
    Seed2.0 Pro

    as “Seed2.0-Pro”
    87.0%
21. 21
    Qwen3.5 122B A10B

    as “Qwen3.5-122B-A10B”
    86.7%
22. 22
    Seed1.6

    as “Seed1.6-Thinking”
    86.6%
23. 22
    Seed1.6 Base

    as “Seed1.6-Base”
    86.6%
24. 24
    GPT-5.1
    86.4%
25. 24
    Seed1.6 Ada

    as “Seed1.6-Ada-Thinking”
    86.4%

History builds with every daily capture. One capture so far.

AA Intelligence

#1 Claude Opus 5.5

HLE

#1 GPT-6 Astra

GPQA Diamond

#1 GPT-6 Astra

Epoch ECI

#1 GPT-6 Astra

ARC-AGI-2

#1 GPT-6 Astra

LiveBench

#1 Claude Fable 5.1

Open LLM LB

#1 none