← BFCL leaderboards

Format Variant 4

BFCL · 40 models

RankModelScore
1GPT-4.1-mini-2025-04-14 (Prompt)83.5
2Gemma-3-27b-it (Prompt)82.5
2Qwen3-235B-A22B-Instruct-2507 (Prompt)82.5
4Claude-Opus-4-5-20251101 (Prompt)81.5
4GPT-4.1-2025-04-14 (Prompt)81.5
4GPT-4.1-nano-2025-04-14 (Prompt)81.5
7Gemini-3-Pro-Preview (Prompt)81
7Mistral-Small-2506 (Prompt)81
7Qwen3-14B (Prompt)81
10Gemini-2.5-Flash (Prompt)80.5
10o3-2025-04-16 (Prompt)80.5
12Qwen3-32B (Prompt)80
12ToolACE-2-8B (FC)80
12mistral-large-2411 (Prompt)80
15Qwen3-30B-A3B-Instruct-2507 (Prompt)79.5
15Qwen3-8B (Prompt)79.5
17Grok-4-0709 (Prompt)79
18o4-mini-2025-04-16 (Prompt)78.5
19CoALM-8B77
19DeepSeek-V3.2-Exp (Prompt + Thinking)77
19GPT-5.2-2025-12-11 (Prompt)77
19Qwen3-4B-Instruct-2507 (Prompt)77
23Gemma-3-12b-it (Prompt)76.5
24Bielik-11B-v2.3-Instruct (Prompt)74.5
24GPT-5-mini-2025-08-07 (Prompt)74.5
24GPT-5-nano-2025-08-07 (Prompt)74.5
27Open-Mistral-Nemo-2407 (Prompt)74
28Llama-3.1-8B-Instruct (Prompt)73.5
29Gemini-2.5-Flash-Lite (Prompt)72.5
29Phi-4 (Prompt)72.5
31CoALM-70B72
32Mistral-Medium-250570
33Claude-Haiku-4-5-20251001 (Prompt)66
34Claude-Sonnet-4-5-20250929 (Prompt)64.5
35Gemma-3-4b-it (Prompt)63.5
36RZN-T (Prompt)56.5
37Qwen3-0.6B (Prompt)53
38MiniCPM3-4B (Prompt)33
39Gemma-3-1b-it (Prompt)17.5
40Ministral-8B-Instruct-2410 (FC)0