← BFCL leaderboards

Format Variant 16

BFCL · 40 models

RankModelScore
1Claude-Sonnet-4-5-20250929 (Prompt)84
2Qwen3-235B-A22B-Instruct-2507 (Prompt)83
3mistral-large-2411 (Prompt)81.5
4Gemini-3-Pro-Preview (Prompt)81
5GPT-4.1-mini-2025-04-14 (Prompt)80
5Qwen3-32B (Prompt)80
7Phi-4 (Prompt)79
7Qwen3-14B (Prompt)79
7o3-2025-04-16 (Prompt)79
10Claude-Opus-4-5-20251101 (Prompt)78.5
10Gemini-2.5-Flash (Prompt)78.5
10Grok-4-0709 (Prompt)78.5
13DeepSeek-V3.2-Exp (Prompt + Thinking)78
14GPT-5.2-2025-12-11 (Prompt)77.5
14Gemma-3-27b-it (Prompt)77.5
16o4-mini-2025-04-16 (Prompt)76
17GPT-4.1-2025-04-14 (Prompt)75.5
17Qwen3-30B-A3B-Instruct-2507 (Prompt)75.5
19Mistral-Medium-250575
20GPT-5-mini-2025-08-07 (Prompt)74
21Gemini-2.5-Flash-Lite (Prompt)71
21Qwen3-8B (Prompt)71
23Mistral-Small-2506 (Prompt)70.5
24GPT-5-nano-2025-08-07 (Prompt)70
24Open-Mistral-Nemo-2407 (Prompt)70
26Qwen3-4B-Instruct-2507 (Prompt)65
27GPT-4.1-nano-2025-04-14 (Prompt)60.5
28Bielik-11B-v2.3-Instruct (Prompt)50.5
29Llama-3.1-8B-Instruct (Prompt)48
30MiniCPM3-4B (Prompt)38
31Claude-Haiku-4-5-20251001 (Prompt)33.5
32Gemma-3-4b-it (Prompt)28.5
33Gemma-3-12b-it (Prompt)26
34ToolACE-2-8B (FC)17.5
35RZN-T (Prompt)15.5
36Qwen3-0.6B (Prompt)13.5
37CoALM-70B0
37CoALM-8B0
37Gemma-3-1b-it (Prompt)0
37Ministral-8B-Instruct-2410 (FC)0