Irrelevance Detection

BFCL · 50 models

Rank	Model	Score
1	Llama-3.1-Nemotron-Ultra-253B-v1 (FC)	100
1	Ministral-8B-Instruct-2410 (FC)	100
3	BitAgent-Bounty-8B	98.3
4	Claude-Haiku-4-5-20251001 (Prompt)	96.83
5	Claude-Sonnet-4-5-20250929 (Prompt)	96.72
6	Gemini-2.5-Flash (FC)	92.76
7	DeepSeek-V3.2-Exp (FC)	92.19
8	Gemini-2.5-Flash-Lite (Prompt)	92.08
9	Gemini-2.5-Flash-Lite (FC)	90.84
10	Mistral-Medium-2505 (FC)	90.16
11	GPT-5-mini-2025-08-07 (FC)	89.93
12	Claude-Opus-4-5-20251101 (Prompt)	88.57
12	Hammer2.1-7b (FC)	88.57
14	Gemini-2.5-Flash (Prompt)	88.01
15	Mistral-small-2506 (FC)	87.56
16	Moonshotai-Kimi-K2-Instruct (FC)	86.76
16	Phi-4 (Prompt)	86.76
18	GPT-5-nano-2025-08-07 (FC)	86.54
19	Command A Reasoning (FC)	86.43
20	Claude-Haiku-4-5-20251001 (FC)	85.63
21	Claude-Sonnet-4-5-20250929 (FC)	85.29
22	o4-mini-2025-04-16 (Prompt)	84.73
23	GLM-4.6 (FC thinking)	84.5
23	ToolACE-2-8B (FC)	84.5
25	Qwen3-14B (Prompt)	83.94
25	o3-2025-04-16 (FC)	83.94
27	Command R7B (FC)	83.71
28	Claude-Opus-4-5-20251101 (FC)	83.6
29	GPT-4.1-2025-04-14 (FC)	83.03
30	CoALM-8B	82.13
30	Command A (FC)	82.13
32	GPT-5.2-2025-12-11 (Prompt)	82.01
32	Gemini-3-Pro-Preview (Prompt)	82.01
32	Nanbeige4-3B-Thinking-2511 (FC)	82.01
35	Qwen3-0.6B (Prompt)	81.67
36	o4-mini-2025-04-16 (FC)	81.56
36	palmyra-x-004 (FC)	81.56
38	Grok-4-0709 (Prompt)	81.11
38	Qwen3-4B-Instruct-2507 (FC)	81.11
40	Hammer2.1-3b (FC)	81
41	GPT-4.1-mini-2025-04-14 (FC)	80.88
41	o3-2025-04-16 (Prompt)	80.88
43	RZN-T (Prompt)	80.66
44	Qwen3-32B (Prompt)	80.2
45	CoALM-70B	79.64
46	Arch-Agent-32B	79.3
46	Qwen3-235B-A22B-Instruct-2507 (FC)	79.3
48	Falcon3-1B-Instruct (FC)	79.19
48	Qwen3-0.6B (FC)	79.19
50	GPT-4.1-nano-2025-04-14 (Prompt)	78.96