← BFCL leaderboards

Format Variant 18

BFCL · 40 models

RankModelScore
1Claude-Sonnet-4-5-20250929 (Prompt)84.5
2Gemini-3-Pro-Preview (Prompt)83
3GPT-5.2-2025-12-11 (Prompt)82.5
4Qwen3-14B (Prompt)82
4Qwen3-235B-A22B-Instruct-2507 (Prompt)82
6Gemini-2.5-Flash (Prompt)81.5
6Qwen3-30B-A3B-Instruct-2507 (Prompt)81.5
8GPT-4.1-mini-2025-04-14 (Prompt)81
8Qwen3-32B (Prompt)81
10mistral-large-2411 (Prompt)80.5
11Grok-4-0709 (Prompt)79.5
12Claude-Opus-4-5-20251101 (Prompt)79
12DeepSeek-V3.2-Exp (Prompt + Thinking)79
12Gemma-3-27b-it (Prompt)79
12Mistral-Medium-250579
16o4-mini-2025-04-16 (Prompt)77.5
17Phi-4 (Prompt)77
18Qwen3-8B (Prompt)76
18o3-2025-04-16 (Prompt)76
20Open-Mistral-Nemo-2407 (Prompt)75.5
21Mistral-Small-2506 (Prompt)74.5
22GPT-5-mini-2025-08-07 (Prompt)73.5
23GPT-4.1-2025-04-14 (Prompt)71.5
23GPT-5-nano-2025-08-07 (Prompt)71.5
25Gemini-2.5-Flash-Lite (Prompt)70.5
26Qwen3-4B-Instruct-2507 (Prompt)67.5
27GPT-4.1-nano-2025-04-14 (Prompt)58
28Llama-3.1-8B-Instruct (Prompt)57.5
29Bielik-11B-v2.3-Instruct (Prompt)57
30MiniCPM3-4B (Prompt)44.5
31Claude-Haiku-4-5-20251001 (Prompt)29
32RZN-T (Prompt)27
33Gemma-3-4b-it (Prompt)26.5
33Qwen3-0.6B (Prompt)26.5
35Gemma-3-12b-it (Prompt)20.5
36ToolACE-2-8B (FC)12
37CoALM-70B0
37CoALM-8B0
37Gemma-3-1b-it (Prompt)0
37Ministral-8B-Instruct-2410 (FC)0