← BFCL leaderboards

Format Variant 7

BFCL · 40 models

RankModelScore
1Claude-Sonnet-4-5-20250929 (Prompt)85.5
2Qwen3-32B (Prompt)84
3Claude-Opus-4-5-20251101 (Prompt)83.5
3Gemini-2.5-Flash (Prompt)83.5
5Grok-4-0709 (Prompt)83
5Qwen3-14B (Prompt)83
7Gemini-3-Pro-Preview (Prompt)82.5
8Qwen3-8B (Prompt)82
9Qwen3-235B-A22B-Instruct-2507 (Prompt)80.5
10GPT-4.1-2025-04-14 (Prompt)80
10mistral-large-2411 (Prompt)80
12GPT-4.1-mini-2025-04-14 (Prompt)79.5
12o4-mini-2025-04-16 (Prompt)79.5
14GPT-5.2-2025-12-11 (Prompt)78
15Open-Mistral-Nemo-2407 (Prompt)77
16DeepSeek-V3.2-Exp (Prompt + Thinking)76.5
17GPT-5-mini-2025-08-07 (Prompt)76
18Qwen3-30B-A3B-Instruct-2507 (Prompt)74.5
19GPT-5-nano-2025-08-07 (Prompt)73
19o3-2025-04-16 (Prompt)73
21Mistral-Medium-250571
22Qwen3-4B-Instruct-2507 (Prompt)70.5
23Bielik-11B-v2.3-Instruct (Prompt)70
24Gemini-2.5-Flash-Lite (Prompt)68.5
25Gemma-3-27b-it (Prompt)65.5
26Claude-Haiku-4-5-20251001 (Prompt)61
27Mistral-Small-2506 (Prompt)54.5
28Gemma-3-12b-it (Prompt)52.5
29CoALM-70B23.5
30MiniCPM3-4B (Prompt)17
31GPT-4.1-nano-2025-04-14 (Prompt)8.5
32Qwen3-0.6B (Prompt)7
33Gemma-3-4b-it (Prompt)6
34RZN-T (Prompt)5.5
35Llama-3.1-8B-Instruct (Prompt)3
36Phi-4 (Prompt)1.5
37CoALM-8B0
37Gemma-3-1b-it (Prompt)0
37Ministral-8B-Instruct-2410 (FC)0
37ToolACE-2-8B (FC)0