← BFCL leaderboards

Format Variant 10

BFCL · 40 models

RankModelScore
1Claude-Sonnet-4-5-20250929 (Prompt)86.5
2Claude-Opus-4-5-20251101 (Prompt)83.5
3Claude-Haiku-4-5-20251001 (Prompt)83
3Gemma-3-27b-it (Prompt)83
5Mistral-Small-2506 (Prompt)82.5
6Phi-4 (Prompt)82
6mistral-large-2411 (Prompt)82
8Gemma-3-12b-it (Prompt)81.5
8Qwen3-14B (Prompt)81.5
8Qwen3-8B (Prompt)81.5
11GPT-4.1-2025-04-14 (Prompt)81
12Gemini-2.5-Flash (Prompt)80.5
12Qwen3-235B-A22B-Instruct-2507 (Prompt)80.5
14GPT-4.1-mini-2025-04-14 (Prompt)80
14Gemini-3-Pro-Preview (Prompt)80
16Grok-4-0709 (Prompt)79.5
16Qwen3-32B (Prompt)79.5
18o3-2025-04-16 (Prompt)79
19Mistral-Medium-250578.5
20GPT-5.2-2025-12-11 (Prompt)78
20Qwen3-30B-A3B-Instruct-2507 (Prompt)78
22Open-Mistral-Nemo-2407 (Prompt)77.5
22o4-mini-2025-04-16 (Prompt)77.5
24DeepSeek-V3.2-Exp (Prompt + Thinking)77
25Bielik-11B-v2.3-Instruct (Prompt)75.5
25Qwen3-4B-Instruct-2507 (Prompt)75.5
27GPT-5-mini-2025-08-07 (Prompt)75
28GPT-5-nano-2025-08-07 (Prompt)73.5
29GPT-4.1-nano-2025-04-14 (Prompt)70.5
29Gemma-3-4b-it (Prompt)70.5
29Llama-3.1-8B-Instruct (Prompt)70.5
32MiniCPM3-4B (Prompt)66
33CoALM-8B61
34Qwen3-0.6B (Prompt)60
35Gemini-2.5-Flash-Lite (Prompt)59.5
36RZN-T (Prompt)55.5
37Gemma-3-1b-it (Prompt)21
38ToolACE-2-8B (FC)20.5
39CoALM-70B10.5
40Ministral-8B-Instruct-2410 (FC)0