Web Search Base

BFCL · 50 models

Rank	Model	Score
1	GPT-5-mini-2025-08-07 (FC)	87
2	Claude-Haiku-4-5-20251001 (FC)	86
3	Claude-Opus-4-5-20251101 (FC)	84
4	Claude-Sonnet-4-5-20250929 (FC)	82
4	Grok-4-1-fast-reasoning (FC)	82
6	DeepSeek-V3.2-Exp (FC)	80
6	Grok-4-0709 (FC)	80
8	GLM-4.6 (FC thinking)	79
8	o3-2025-04-16 (FC)	79
10	GPT-5.2-2025-12-11 (FC)	78
10	Gemini-3-Pro-Preview (Prompt)	78
12	o4-mini-2025-04-16 (FC)	75
13	GPT-5-nano-2025-08-07 (FC)	74
13	Grok-4-0709 (Prompt)	74
13	Grok-4-1-fast-non-reasoning (FC)	74
16	o4-mini-2025-04-16 (Prompt)	73
17	Moonshotai-Kimi-K2-Instruct (FC)	72
18	GPT-4.1-2025-04-14 (FC)	67
19	Command A Reasoning (FC)	65
20	DeepSeek-V3.2-Exp (Prompt + Thinking)	64
21	Gemini-3-Pro-Preview (FC)	63
22	GPT-4.1-mini-2025-04-14 (FC)	62
23	Command A (FC)	60
23	Gemini-2.5-Flash (Prompt)	60
25	Gemini-2.5-Flash (FC)	59
26	Qwen3-235B-A22B-Instruct-2507 (FC)	57
27	Qwen3-235B-A22B-Instruct-2507 (Prompt)	56
28	o3-2025-04-16 (Prompt)	51
29	Nanbeige3.5-Pro-Thinking (FC)	47
30	GPT-5.2-2025-12-11 (Prompt)	45
31	Command R7B (FC)	43
32	Mistral-Medium-2505	41
32	mistral-large-2411 (FC)	41
34	GPT-4.1-2025-04-14 (Prompt)	40
35	Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)	39
36	Mistral-small-2506 (FC)	37
36	xLAM-2-32b-fc-r (FC)	37
38	Mistral-Medium-2505 (FC)	36
39	Qwen3-32B (Prompt)	34
40	Nanbeige4-3B-Thinking-2511 (FC)	31
41	mistral-large-2411 (Prompt)	28
42	Gemini-2.5-Flash-Lite (FC)	26
43	Qwen3-32B (FC)	25
44	Qwen3-30B-A3B-Instruct-2507 (FC)	21
45	Claude-Haiku-4-5-20251001 (Prompt)	20
46	Qwen3-8B (Prompt)	19
47	Llama-4-Scout-17B-16E-Instruct (FC)	18
48	xLAM-2-70b-fc-r (FC)	17
49	Claude-Sonnet-4-5-20250929 (Prompt)	16
50	Qwen3-30B-A3B-Instruct-2507 (Prompt)	15