← BFCL leaderboards

Format Variant 12

BFCL · 40 models

RankModelScore
1Claude-Sonnet-4-5-20250929 (Prompt)87.5
2Claude-Opus-4-5-20251101 (Prompt)86
3Gemini-3-Pro-Preview (Prompt)85
4Gemma-3-27b-it (Prompt)84.5
4Qwen3-32B (Prompt)84.5
6Mistral-Small-2506 (Prompt)84
7Gemma-3-12b-it (Prompt)83
7Phi-4 (Prompt)83
7Qwen3-14B (Prompt)83
10Claude-Haiku-4-5-20251001 (Prompt)82.5
10Gemini-2.5-Flash (Prompt)82.5
10Qwen3-4B-Instruct-2507 (Prompt)82.5
13Qwen3-235B-A22B-Instruct-2507 (Prompt)82
14GPT-4.1-mini-2025-04-14 (Prompt)81.5
15GPT-4.1-2025-04-14 (Prompt)81
16DeepSeek-V3.2-Exp (Prompt + Thinking)80.5
16GPT-5.2-2025-12-11 (Prompt)80.5
16Qwen3-30B-A3B-Instruct-2507 (Prompt)80.5
16o3-2025-04-16 (Prompt)80.5
20Grok-4-0709 (Prompt)80
21Mistral-Medium-250579.5
21Open-Mistral-Nemo-2407 (Prompt)79.5
21Qwen3-8B (Prompt)79.5
24o4-mini-2025-04-16 (Prompt)78
25Bielik-11B-v2.3-Instruct (Prompt)77.5
26GPT-5-mini-2025-08-07 (Prompt)76.5
27Llama-3.1-8B-Instruct (Prompt)75
28mistral-large-2411 (Prompt)72.5
29GPT-5-nano-2025-08-07 (Prompt)72
30Gemma-3-4b-it (Prompt)71.5
31MiniCPM3-4B (Prompt)71
32CoALM-8B65.5
33RZN-T (Prompt)63.5
34Gemini-2.5-Flash-Lite (Prompt)61
35Qwen3-0.6B (Prompt)60.5
36GPT-4.1-nano-2025-04-14 (Prompt)46
37CoALM-70B45.5
38Gemma-3-1b-it (Prompt)20
39ToolACE-2-8B (FC)17
40Ministral-8B-Instruct-2410 (FC)0