← BFCL leaderboards

Format Variant 1

BFCL · 40 models

RankModelScore
1Claude-Sonnet-4-5-20250929 (Prompt)87
2Claude-Opus-4-5-20251101 (Prompt)83.5
2mistral-large-2411 (Prompt)83.5
4Qwen3-8B (Prompt)82
5GPT-4.1-2025-04-14 (Prompt)81.5
5GPT-4.1-mini-2025-04-14 (Prompt)81.5
5Gemini-2.5-Flash (Prompt)81.5
5Gemini-3-Pro-Preview (Prompt)81.5
5Qwen3-32B (Prompt)81.5
10Qwen3-14B (Prompt)81
11Mistral-Small-2506 (Prompt)80.5
11Qwen3-235B-A22B-Instruct-2507 (Prompt)80.5
13Qwen3-4B-Instruct-2507 (Prompt)80
14DeepSeek-V3.2-Exp (Prompt + Thinking)79.5
15o3-2025-04-16 (Prompt)78
16Gemma-3-27b-it (Prompt)77
17GPT-5.2-2025-12-11 (Prompt)76.5
17Grok-4-0709 (Prompt)76.5
17Qwen3-30B-A3B-Instruct-2507 (Prompt)76.5
20GPT-5-mini-2025-08-07 (Prompt)76
21Open-Mistral-Nemo-2407 (Prompt)75.5
21Phi-4 (Prompt)75.5
21o4-mini-2025-04-16 (Prompt)75.5
24Gemma-3-12b-it (Prompt)73
25GPT-5-nano-2025-08-07 (Prompt)68.5
26Claude-Haiku-4-5-20251001 (Prompt)68
27Bielik-11B-v2.3-Instruct (Prompt)65.5
28Mistral-Medium-250559.5
29Gemma-3-4b-it (Prompt)54
30Gemini-2.5-Flash-Lite (Prompt)52.5
31MiniCPM3-4B (Prompt)40
31RZN-T (Prompt)40
33GPT-4.1-nano-2025-04-14 (Prompt)36.5
34Qwen3-0.6B (Prompt)35
35Llama-3.1-8B-Instruct (Prompt)34
36ToolACE-2-8B (FC)24
37CoALM-70B13
38Gemma-3-1b-it (Prompt)3
39CoALM-8B1
40Ministral-8B-Instruct-2410 (FC)0