← BFCL leaderboards

Format Variant 11

BFCL · 40 models

RankModelScore
1Claude-Sonnet-4-5-20250929 (Prompt)88
2Claude-Opus-4-5-20251101 (Prompt)82.5
2Gemini-3-Pro-Preview (Prompt)82.5
2Mistral-Small-2506 (Prompt)82.5
2Qwen3-235B-A22B-Instruct-2507 (Prompt)82.5
6Gemma-3-27b-it (Prompt)82
6Grok-4-0709 (Prompt)82
8Claude-Haiku-4-5-20251001 (Prompt)81.5
9Qwen3-32B (Prompt)81
10DeepSeek-V3.2-Exp (Prompt + Thinking)80.5
10o3-2025-04-16 (Prompt)80.5
12GPT-4.1-2025-04-14 (Prompt)80
12GPT-5.2-2025-12-11 (Prompt)80
12Gemma-3-12b-it (Prompt)80
12Qwen3-30B-A3B-Instruct-2507 (Prompt)80
16GPT-4.1-mini-2025-04-14 (Prompt)79.5
16Open-Mistral-Nemo-2407 (Prompt)79.5
18Gemini-2.5-Flash (Prompt)79
18Mistral-Medium-250579
18Phi-4 (Prompt)79
21Qwen3-8B (Prompt)78.5
22o4-mini-2025-04-16 (Prompt)78
23Qwen3-14B (Prompt)76.5
24mistral-large-2411 (Prompt)76
25Qwen3-4B-Instruct-2507 (Prompt)75.5
26Bielik-11B-v2.3-Instruct (Prompt)74.5
27GPT-5-mini-2025-08-07 (Prompt)73
28GPT-5-nano-2025-08-07 (Prompt)71.5
29MiniCPM3-4B (Prompt)70
30Llama-3.1-8B-Instruct (Prompt)69.5
31Gemma-3-4b-it (Prompt)67.5
32GPT-4.1-nano-2025-04-14 (Prompt)65
33CoALM-8B64.5
34Gemini-2.5-Flash-Lite (Prompt)62.5
35RZN-T (Prompt)58.5
36Qwen3-0.6B (Prompt)57
37CoALM-70B32.5
37ToolACE-2-8B (FC)32.5
39Gemma-3-1b-it (Prompt)21
40Ministral-8B-Instruct-2410 (FC)0