Memory Summary

BFCL · 50 models

Rank	Model	Score
1	Claude-Opus-4-5-20251101 (FC)	73.76
2	Claude-Sonnet-4-5-20250929 (FC)	64.95
3	Gemini-3-Pro-Preview (Prompt)	61.72
4	Grok-4-0709 (FC)	55.91
5	GLM-4.6 (FC thinking)	55.7
6	Gemini-3-Pro-Preview (FC)	54.84
7	Claude-Haiku-4-5-20251001 (FC)	54.41
8	DeepSeek-V3.2-Exp (FC)	54.19
9	Grok-4-1-fast-reasoning (FC)	53.98
10	o3-2025-04-16 (Prompt)	51.83
11	Grok-4-0709 (Prompt)	50.54
12	o3-2025-04-16 (FC)	47.31
13	GPT-5.2-2025-12-11 (FC)	45.81
14	Nanbeige3.5-Pro-Thinking (FC)	45.16
15	GPT-5-mini-2025-08-07 (FC)	44.3
16	DeepSeek-V3.2-Exp (Prompt + Thinking)	44.09
17	Gemini-2.5-Flash (FC)	41.29
18	Gemini-2.5-Flash (Prompt)	38.71
19	Nanbeige4-3B-Thinking-2511 (FC)	36.77
20	o4-mini-2025-04-16 (Prompt)	35.27
21	o4-mini-2025-04-16 (FC)	34.19
22	GPT-5-mini-2025-08-07 (Prompt)	29.25
23	Moonshotai-Kimi-K2-Instruct (FC)	29.03
24	Command A Reasoning (FC)	28.82
25	Falcon3-10B-Instruct (FC)	27.53
25	Gemma-3-12b-it (Prompt)	27.53
27	GPT-4.1-mini-2025-04-14 (FC)	26.88
28	Qwen3-32B (FC)	26.67
29	Grok-4-1-fast-non-reasoning (FC)	26.24
30	mistral-large-2411 (FC)	24.95
31	GPT-5-nano-2025-08-07 (FC)	24.73
31	Phi-4 (Prompt)	24.73
33	GPT-5-nano-2025-08-07 (Prompt)	24.52
34	GPT-4.1-mini-2025-04-14 (Prompt)	24.3
35	GPT-4.1-2025-04-14 (FC)	23.87
35	Qwen3-235B-A22B-Instruct-2507 (FC)	23.87
35	Qwen3-4B-Instruct-2507 (Prompt)	23.87
38	mistral-large-2411 (Prompt)	23.66
39	Mistral-Medium-2505 (FC)	23.01
40	Mistral-Medium-2505	21.72
41	GPT-4.1-2025-04-14 (Prompt)	21.51
42	xLAM-2-32b-fc-r (FC)	20.86
43	Falcon3-7B-Instruct (FC)	20.65
43	Gemini-2.5-Flash-Lite (FC)	20.65
45	Qwen3-14B (FC)	19.57
46	Qwen3-235B-A22B-Instruct-2507 (Prompt)	19.35
47	GPT-4.1-nano-2025-04-14 (FC)	18.92
47	Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)	18.92
49	ToolACE-2-8B (FC)	18.49
50	Mistral-small-2506 (FC)	18.06