Live Acc

BFCL · 50 models

Rank	Model	Score
1	BitAgent-Bounty-8B	93.12
2	Gemini-3-Pro-Preview (Prompt)	83.12
3	Qwen3-32B (FC)	82.01
3	Qwen3-32B (Prompt)	82.01
5	mistral-large-2411 (FC)	81.87
6	Gemini-3-Pro-Preview (FC)	81.72
7	Claude-Sonnet-4-5-20250929 (FC)	81.13
8	GLM-4.6 (FC thinking)	80.9
9	Amazon-Nova-2-Lite-v1:0 (FC)	80.83
10	Arch-Agent-32B	80.68
11	Qwen3-8B (FC)	80.53
12	Qwen3-8B (Prompt)	80.09
13	Qwen3-14B (FC)	80.01
14	Claude-Opus-4-5-20251101 (FC)	79.79
15	Nanbeige4-3B-Thinking-2511 (FC)	79.42
16	Qwen3-14B (Prompt)	79.35
17	Mistral-Small-2506 (Prompt)	79.05
18	GPT-4.1-2025-04-14 (Prompt)	78.9
19	Claude-Haiku-4-5-20251001 (FC)	78.68
19	Moonshotai-Kimi-K2-Instruct (FC)	78.68
19	Qwen3-235B-A22B-Instruct-2507 (Prompt)	78.68
22	Command A Reasoning (FC)	78.61
23	Amazon-Nova-Pro-v1:0 (FC)	78.53
23	Command A (FC)	78.53
25	Grok-4-1-fast-reasoning (FC)	78.46
26	Qwen3-30B-A3B-Instruct-2507 (Prompt)	78.39
27	Gemini-2.5-Flash (Prompt)	78.16
28	Grok-4-1-fast-non-reasoning (FC)	77.94
28	Qwen3-30B-A3B-Instruct-2507 (FC)	77.94
30	palmyra-x-004 (FC)	77.87
31	ToolACE-2-8B (FC)	77.42
32	Mistral-small-2506 (FC)	77.28
33	Llama-3.3-70B-Instruct (FC)	76.61
34	Qwen3-4B-Instruct-2507 (FC)	76.39
35	Claude-Opus-4-5-20251101 (Prompt)	76.02
35	DeepSeek-V3.2-Exp (Prompt + Thinking)	76.02
37	Grok-4-0709 (FC)	75.57
38	xLAM-2-32b-fc-r (FC)	75.5
39	Falcon3-10B-Instruct (FC)	75.43
40	GPT-4.1-mini-2025-04-14 (Prompt)	74.76
41	Llama-4-Scout-17B-16E-Instruct (FC)	74.69
41	Qwen3-4B-Instruct-2507 (Prompt)	74.69
43	Qwen3-1.7B (FC)	74.61
44	Gemma-3-27b-it (Prompt)	74.54
45	Gemini-2.5-Flash (FC)	74.39
46	Gemma-3-12b-it (Prompt)	74.24
47	Open-Mistral-Nemo-2407 (Prompt)	73.95
48	Open-Mistral-Nemo-2407 (FC)	73.8
49	Llama-4-Maverick-17B-128E-Instruct-FP8 (FC)	73.65
50	o3-2025-04-16 (Prompt)	73.21