Scale SEAL MultiChallenge

1. 1
   Muse Spark
   75.5%
2. 2
   Muse Spark 1.1
   75.3%
3. 3
   Gemini 3.1 Pro Preview

   as “gemini-3.1-pro-preview”
   71.4%
4. 4
   GPT-5.4 Pro

   as “gpt-5.4-pro-2026-03-05”
   69.2%
5. 5
   Gemini 3 Pro

   as “gemini-3-pro-preview”
   65.7%
6. 6
   GPT-5.1

   as “gpt-5.1-2025-11-13-thinking”
   63.4%
7. 7
   GPT-5

   as “gpt-5-thinking”
   63.2%
8. 8
   o3-pro

   as “o3-pro-2025-06-10-reasoning-high”
   62.4%
9. 9
   Kimi K2.5

   as “kimi-k2.5”
   61.4%
10. 10
    Gemini 3.1 Flash-Lite

    as “gemini-3.1-flash-lite-preview”
    60.6%
11. 11
    GPT-5 mini

    as “gpt-5-mini-thinking”
    59.0%
12. 12
    Claude Opus 4.5

    as “claude-opus-4-5-20251101-thinking”
    59.0%
13. 13
    Claude Opus 4

    as “claude-4-opus-thinking”
    58.6%
14. 14
    Claude Opus 4.1

    as “claude-opus-4-1-20250805-thinking”
    57.2%
15. 15
    Claude Sonnet 4

    as “claude-4-sonnet-thinking”
    57.1%
16. 16
    o3

    as “o3-2025-04-16-reasoning-high”
    56.6%
17. 17
    Claude Opus 4.6

    as “claude-opus-4-6 (Non-Thinking)”
    56.0%
18. 18
    Kimi K2 Thinking

    as “kimi-k2-thinking”
    55.4%
19. 19
    Claude Sonnet 4.5

    as “claude-sonnet-4-5-20250929-thinking”
    55.3%
20. 20
    Gemini 2.5 Pro (Jun 2025)

    as “gemini-2-5-pro”
    53.6%
21. 21
    Claude 3 7 Sonnet

    as “claude-3-7-sonnet-thinking”
    51.6%
22. 22
    GPT-5.1 Instant

    as “gpt-5.1-2025-11-13-instant”
    51.2%
23. 23
    Claude 4.5 Haiku

    as “claude-haiku-4-5-20251001-thinking”
    50.5%
24. 24
    DeepSeek V3P1

    as “deepseek-v3p1”
    46.1%
25. 25
    gpt-oss-120b
    45.3%

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

Text Arena

#1 Claude Fable 5