Berkeley Function Calling Leaderboard

1. 1
   Claude Opus 4.5

   as “Claude-Opus-4-5-20251101 (FC)”
   77.5%
2. 2
   Claude Sonnet 4.5

   as “Claude-Sonnet-4-5-20250929 (FC)”
   73.2%
3. 3
   Gemini 3 Pro

   as “Gemini-3-Pro-Preview (Prompt)”
   72.5%
4. 4
   GLM 4.6

   as “GLM-4.6 (FC thinking)”
   72.4%
5. 5
   Grok 4 1 Fast

   as “Grok-4-1-fast-reasoning (FC)”
   69.6%
6. 6
   Claude 4.5 Haiku

   as “Claude-Haiku-4-5-20251001 (FC)”
   68.7%
7. 7
   o3

   as “o3-2025-04-16 (Prompt)”
   63.0%
8. 8
   Grok 4

   as “Grok-4-0709 (Prompt)”
   63.0%
9. 9
   Moonshotai Kimi K2

   as “Moonshotai-Kimi-K2-Instruct (FC)”
   59.1%
10. 10
    Grok 4 1 Fast Non

    as “Grok-4-1-fast-non-reasoning (FC)”
    58.3%
11. 11
    Command A+

    as “Command A Reasoning (FC)”
    57.1%
12. 12
    DeepSeek-V3.2

    as “DeepSeek-V3.2-Exp (Prompt + Thinking)”
    56.7%
13. 13
    Gemini 2.5 Flash (Sep 2025)

    as “Gemini-2.5-Flash (FC)”
    56.2%
14. 14
    GPT-5.2

    as “GPT-5.2-2025-12-11 (FC)”
    55.9%
15. 15
    GPT-5 mini

    as “GPT-5-mini-2025-08-07 (FC)”
    55.5%
16. 16
    SXlam 2 32b Fc R

    as “xLAM-2-32b-fc-r (FC)”
    54.7%
17. 17
    GPT 4.1

    as “GPT-4.1-2025-04-14 (FC)”
    54.0%
18. 18
    o4-mini

    as “o4-mini-2025-04-16 (FC)”
    53.2%
19. 19
    SXlam 2 70b Fc R

    as “xLAM-2-70b-fc-r (FC)”
    53.1%
20. 20
    Qwen3-235B-A22B-Thinking (Jul 2025)

    as “Qwen3-235B-A22B-Instruct-2507 (Prompt)”
    52.1%
21. 21
    GPT 5 nano

    as “GPT-5-nano-2025-08-07 (FC)”
    51.5%
22. 22
    NNanbeige4 3b

    as “Nanbeige4-3B-Thinking-2511 (FC)”
    51.4%
23. 23
    GPT 4.1 mini

    as “GPT-4.1-mini-2025-04-14 (FC)”
    50.5%
24. 24
    Qwen3 32b

    as “Qwen3-32B (FC)”
    48.7%
25. 25
    NNanbeige3.5 Pro

    as “Nanbeige3.5-Pro-Thinking (FC)”
    47.7%

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

MCP Atlas

#1 Muse Spark 1.1

Search Arena

#1 GPT-5.6 Sol