Aider Polyglot

1. 1
   GPT-5

   as “gpt-5 (high)”
   88.0%
2. 2
   o3-pro

   as “o3-pro (high)”
   84.9%
3. 3
   Gemini 2.5 Pro (Jun 2025)

   as “gemini-2.5-pro-preview-06-05 (32k think)”
   83.1%
4. 4
   o3

   as “o3 (high)”
   81.3%
5. 5
   Grok 4

   as “grok-4 (high)”
   79.6%
6. 6
   o3 GPT 4.1

   as “o3 (high) + gpt-4.1”
   78.2%
7. 7
   Gemini 2.5 Pro 05 06

   as “Gemini 2.5 Pro Preview 05-06”
   76.9%
8. 8
   DeepSeek-V3.2

   as “DeepSeek-V3.2-Exp (Reasoner)”
   74.2%
9. 9
   Gemini 2.5 Pro 03 25

   as “Gemini 2.5 Pro Preview 03-25”
   72.9%
10. 10
    Claude Opus 4

    as “claude-opus-4-20250514 (32k thinking)”
    72.0%
11. 10
    o4-mini

    as “o4-mini (high)”
    72.0%
12. 12
    DeepSeek-R1 (May 2025)

    as “DeepSeek R1 (0528)”
    71.4%
13. 13
    Claude 3 7 Sonnet

    as “claude-3-7-sonnet-20250219 (32k thinking tokens)”
    64.9%
14. 14
    DeepSeek R1 Claude 3 5 Sonnet

    as “DeepSeek R1 + claude-3-5-sonnet-20241022”
    64.0%
15. 15
    o1

    as “o1-2024-12-17 (high)”
    61.7%
16. 16
    Claude Sonnet 4

    as “claude-sonnet-4-20250514 (32k thinking)”
    61.3%
17. 17
    o3 Mini

    as “o3-mini (high)”
    60.4%
18. 18
    Qwen3 235b A22B Diff No Alibaba

    as “Qwen3 235B A22B diff, no think, Alibaba API”
    59.6%
19. 19
    Kimi K2 Thinking

    as “Kimi K2”
    59.1%
20. 20
    DeepSeek V3

    as “DeepSeek V3 (0324)”
    55.1%
21. 20
    Gemini 2.5 Flash (Sep 2025)

    as “gemini-2.5-flash-preview-05-20 (24k think)”
    55.1%
22. 22
    ?Quasar Alpha
    54.7%
23. 23
    Grok 3

    as “Grok 3 Beta”
    53.3%
24. 24
    ?Optimus Alpha
    52.9%
25. 25
    GPT 4.1

    as “gpt-4.1”
    52.4%

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

WebDev Arena

#1 Claude Opus 5.5

SWE-Bench Pro

#1 Claude Opus 5

SWE-bench Verified

#1 Claude Opus 4.5