← BFCL leaderboards

Format Variant 20

BFCL · 40 models

RankModelScore
1Claude-Sonnet-4-5-20250929 (Prompt)83.5
2Gemini-3-Pro-Preview (Prompt)82.5
3GPT-5.2-2025-12-11 (Prompt)79.5
4Qwen3-235B-A22B-Instruct-2507 (Prompt)78.5
5Grok-4-0709 (Prompt)77.5
6Claude-Opus-4-5-20251101 (Prompt)77
6o3-2025-04-16 (Prompt)77
8GPT-4.1-2025-04-14 (Prompt)76
9Gemini-2.5-Flash (Prompt)74.5
10Qwen3-30B-A3B-Instruct-2507 (Prompt)74
11DeepSeek-V3.2-Exp (Prompt + Thinking)73
11o4-mini-2025-04-16 (Prompt)73
13GPT-5-mini-2025-08-07 (Prompt)72.5
13Qwen3-4B-Instruct-2507 (Prompt)72.5
15Phi-4 (Prompt)71.5
16Mistral-Medium-250571
17GPT-5-nano-2025-08-07 (Prompt)70.5
18Gemma-3-27b-it (Prompt)70
18Qwen3-32B (Prompt)70
18mistral-large-2411 (Prompt)70
21Qwen3-14B (Prompt)69.5
22Open-Mistral-Nemo-2407 (Prompt)68.5
22Qwen3-8B (Prompt)68.5
24Gemini-2.5-Flash-Lite (Prompt)64
25Mistral-Small-2506 (Prompt)62.5
26Bielik-11B-v2.3-Instruct (Prompt)61
27GPT-4.1-nano-2025-04-14 (Prompt)58
28GPT-4.1-mini-2025-04-14 (Prompt)57.5
29Gemma-3-12b-it (Prompt)54
30MiniCPM3-4B (Prompt)51.5
31Claude-Haiku-4-5-20251001 (Prompt)30.5
32Gemma-3-4b-it (Prompt)15
33ToolACE-2-8B (FC)8.5
34Llama-3.1-8B-Instruct (Prompt)7.5
35Gemma-3-1b-it (Prompt)0.5
36CoALM-70B0
36CoALM-8B0
36Ministral-8B-Instruct-2410 (FC)0
36Qwen3-0.6B (Prompt)0
36RZN-T (Prompt)0