Web Search Acc

BFCL · 50 models

Rank	Model	Score
1	Claude-Opus-4-5-20251101 (FC)	84.5
2	Claude-Haiku-4-5-20251001 (FC)	83.5
3	Grok-4-1-fast-reasoning (FC)	82.5
4	GPT-5-mini-2025-08-07 (FC)	82
4	Grok-4-0709 (FC)	82
6	Claude-Sonnet-4-5-20250929 (FC)	81
7	Gemini-3-Pro-Preview (Prompt)	80
8	GLM-4.6 (FC thinking)	77.5
9	o3-2025-04-16 (FC)	77
10	GPT-5.2-2025-12-11 (FC)	75.5
10	o4-mini-2025-04-16 (FC)	75.5
12	Grok-4-1-fast-non-reasoning (FC)	75
13	Grok-4-0709 (Prompt)	74
14	GPT-5-nano-2025-08-07 (FC)	72.5
15	o4-mini-2025-04-16 (Prompt)	71.5
16	DeepSeek-V3.2-Exp (FC)	69.5
17	Gemini-3-Pro-Preview (FC)	68.5
18	GPT-4.1-2025-04-14 (FC)	68
19	Moonshotai-Kimi-K2-Instruct (FC)	66.5
20	Gemini-2.5-Flash (Prompt)	62
21	Gemini-2.5-Flash (FC)	59
22	DeepSeek-V3.2-Exp (Prompt + Thinking)	58
23	GPT-4.1-mini-2025-04-14 (FC)	57
24	Command A Reasoning (FC)	55.5
25	Qwen3-235B-A22B-Instruct-2507 (FC)	54
26	Qwen3-235B-A22B-Instruct-2507 (Prompt)	50.5
26	o3-2025-04-16 (Prompt)	50.5
28	Command A (FC)	46.5
29	Nanbeige3.5-Pro-Thinking (FC)	42
30	GPT-5.2-2025-12-11 (Prompt)	40.5
31	Mistral-Medium-2505	39
32	GPT-4.1-2025-04-14 (Prompt)	35
32	Mistral-Medium-2505 (FC)	35
34	Mistral-small-2506 (FC)	31
35	Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)	28
35	mistral-large-2411 (FC)	28
37	Command R7B (FC)	27
38	Qwen3-32B (Prompt)	26
39	xLAM-2-32b-fc-r (FC)	25.5
40	Qwen3-30B-A3B-Instruct-2507 (FC)	22.5
41	Nanbeige4-3B-Thinking-2511 (FC)	21.5
41	Qwen3-32B (FC)	21.5
43	Gemini-2.5-Flash-Lite (FC)	21
44	mistral-large-2411 (Prompt)	20
45	Claude-Haiku-4-5-20251001 (Prompt)	19.5
46	Qwen3-30B-A3B-Instruct-2507 (Prompt)	17.5
47	Claude-Sonnet-4-5-20250929 (Prompt)	16
48	xLAM-2-70b-fc-r (FC)	15
49	Llama-4-Scout-17B-16E-Instruct (FC)	14.5
50	GPT-5-nano-2025-08-07 (Prompt)	13.5