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	97.48
4	Claude-Haiku-4-5-20251001 (Prompt)	95.29
5	Claude-Sonnet-4-5-20250929 (Prompt)	95.03
6	Gemini-2.5-Flash (FC)	93.67
7	Gemini-2.5-Flash-Lite (Prompt)	93.33
8	DeepSeek-V3.2-Exp (FC)	93.18
9	Gemini-2.5-Flash-Lite (FC)	92.5
10	Mistral-Medium-2505 (FC)	91.95
11	Gemini-2.5-Flash (Prompt)	91.09
12	GPT-5-mini-2025-08-07 (FC)	91.01
13	ToolACE-2-8B (FC)	90.79
14	Claude-Opus-4-5-20251101 (Prompt)	90.75
15	Hammer2.1-7b (FC)	90.12
16	GPT-5-nano-2025-08-07 (FC)	89.1
17	Mistral-small-2506 (FC)	87.94
18	Phi-4 (Prompt)	87.55
19	Moonshotai-Kimi-K2-Instruct (FC)	87.34
20	Falcon3-1B-Instruct (FC)	87.3
21	GPT-5.2-2025-12-11 (Prompt)	87.26
22	Qwen3-14B (Prompt)	87.18
23	o4-mini-2025-04-16 (Prompt)	87.16
24	CoALM-8B	86.9
25	Command A Reasoning (FC)	86.75
26	Claude-Sonnet-4-5-20250929 (FC)	86.61
27	GPT-4.1-2025-04-14 (FC)	86.52
28	o3-2025-04-16 (FC)	86.13
29	Hammer2.1-3b (FC)	86.12
30	CoALM-70B	85.65
31	Gemini-3-Pro-Preview (Prompt)	85.59
32	Claude-Haiku-4-5-20251001 (FC)	85.11
33	GLM-4.6 (FC thinking)	84.96
34	Qwen3-4B-Instruct-2507 (FC)	84.93
35	Claude-Opus-4-5-20251101 (FC)	84.72
36	Grok-4-0709 (Prompt)	84.3
37	Command A (FC)	84.19
38	GPT-4.1-2025-04-14 (Prompt)	83.99
39	o3-2025-04-16 (Prompt)	83.98
40	o4-mini-2025-04-16 (FC)	83.91
41	GPT-4.1-nano-2025-04-14 (Prompt)	83.44
42	Nanbeige4-3B-Thinking-2511 (FC)	83.09
43	Qwen3-0.6B (Prompt)	82.5
44	RZN-T (Prompt)	82.41
45	Qwen3-32B (Prompt)	82.39
46	Qwen3-8B (Prompt)	82.27
47	Arch-Agent-32B	82.15
48	Amazon-Nova-2-Lite-v1:0 (FC)	82.11
49	Qwen3-14B (FC)	81.94
50	Qwen3-235B-A22B-Instruct-2507 (FC)	81.73