Agentic

BFCL · 50 models

Rank	Model	Score
1	Claude-Opus-4-5-20251101 (FC)	79.13
2	Claude-Sonnet-4-5-20250929 (FC)	72.97
3	Gemini-3-Pro-Preview (Prompt)	70.86
4	Grok-4-0709 (FC)	68.96
5	Claude-Haiku-4-5-20251001 (FC)	68.95
6	Grok-4-1-fast-reasoning (FC)	68.24
7	GLM-4.6 (FC thinking)	66.6
8	GPT-5-mini-2025-08-07 (FC)	63.15
9	Grok-4-0709 (Prompt)	62.27
10	o3-2025-04-16 (FC)	62.16
11	DeepSeek-V3.2-Exp (FC)	61.85
12	Gemini-3-Pro-Preview (FC)	61.67
13	GPT-5.2-2025-12-11 (FC)	60.65
14	o4-mini-2025-04-16 (FC)	54.85
15	o4-mini-2025-04-16 (Prompt)	53.38
16	o3-2025-04-16 (Prompt)	51.16
17	DeepSeek-V3.2-Exp (Prompt + Thinking)	51.04
18	Grok-4-1-fast-non-reasoning (FC)	50.62
19	Gemini-2.5-Flash (Prompt)	50.35
20	Gemini-2.5-Flash (FC)	50.15
21	GPT-5-nano-2025-08-07 (FC)	48.62
22	Moonshotai-Kimi-K2-Instruct (FC)	47.77
23	GPT-4.1-2025-04-14 (FC)	45.94
24	Nanbeige3.5-Pro-Thinking (FC)	43.58
25	Command A Reasoning (FC)	42.16
26	GPT-4.1-mini-2025-04-14 (FC)	41.94
27	Qwen3-235B-A22B-Instruct-2507 (FC)	38.94
28	Qwen3-235B-A22B-Instruct-2507 (Prompt)	34.93
29	Command A (FC)	31.53
30	Mistral-Medium-2505	30.36
31	Nanbeige4-3B-Thinking-2511 (FC)	29.14
32	Mistral-Medium-2505 (FC)	29.01
33	GPT-4.1-2025-04-14 (Prompt)	28.25
34	mistral-large-2411 (FC)	26.47
35	Mistral-small-2506 (FC)	24.53
36	Qwen3-32B (FC)	24.08
37	Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)	23.46
38	xLAM-2-32b-fc-r (FC)	23.18
39	GPT-5.2-2025-12-11 (Prompt)	22.19
40	mistral-large-2411 (Prompt)	21.83
41	Qwen3-32B (Prompt)	20.85
42	Gemini-2.5-Flash-Lite (FC)	20.82
43	Qwen3-30B-A3B-Instruct-2507 (FC)	20.07
44	GPT-5-nano-2025-08-07 (Prompt)	19.01
45	GPT-5-mini-2025-08-07 (Prompt)	18.87
46	Command R7B (FC)	16.08
47	Gemma-3-12b-it (Prompt)	15.76
48	GPT-4.1-nano-2025-04-14 (FC)	14.96
49	Qwen3-14B (FC)	14.78
50	xLAM-2-70b-fc-r (FC)	14.7