Time to First Token

Artificial Analysis · 50 models

Rank	Model	Score
1	Gemini 2.5 Flash-Lite (Non-reasoning)	0.29
2	Gemini 2.5 Flash (Non-reasoning)	0.38
3	North Mini Code	0.44
4	Command A+	0.45
5	Grok 4.20 0309 v2 (Non-reasoning)	0.5
6	Qwen3.5 9B (Non-reasoning)	0.51
7	Celeris-1	0.54
7	Claude 4.5 Haiku (Non-reasoning)	0.54
7	NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)	0.54
10	Qwen3 30B A3B (Reasoning)	0.55
11	NVIDIA Nemotron Nano 9B V2 (Reasoning)	0.56
11	Qwen3 30B A3B (Non-reasoning)	0.56
13	Nemotron 3.5 Lightning	0.57
14	DeepSeek V3 0324	0.64
15	Grok 4.3 (Non-reasoning)	0.66
16	Beam 1.0	0.69
17	DeepSeek V3.1 Terminus (Non-reasoning)	0.72
17	Nemotron 3.5 Super VL	0.72
17	gpt-oss-20b (High)	0.72
20	GPT-5.4 mini (Non-reasoning)	0.73
21	Muse Spark Open (Xhigh)	0.74
21	gpt-oss-120b (Low)	0.74
23	Gemma 4 E4B (Non-reasoning)	0.75
23	gpt-oss-120b (High)	0.75
25	GPT-5.4 nano (Non-reasoning)	0.76
26	GPT-5 nano (Minimal)	0.78
26	Gemini 3.5 Flash (Minimal)	0.78
26	Nova Micro	0.78
26	gpt-oss-20b (Low)	0.78
30	Qwen3 235B A22B 2507 (Reasoning)	0.79
31	GPT-4.1 mini	0.8
31	GPT-5.4 (Non-reasoning)	0.8
33	Claude Sonnet 5 (Non-reasoning, High)	0.81
33	GPT-5.6 Luna (Non-reasoning)	0.81
33	Gemma 4 E4B (Reasoning)	0.81
33	Ministral 3 3B	0.81
37	GPT-5.6 Terra (Non-reasoning)	0.82
37	GPT-6 Luna (Non-reasoning)	0.82
39	GPT-5.2 (Non-reasoning)	0.83
39	Llama 4 Scout	0.83
39	Qwen3.5 4B (Non-reasoning)	0.83
42	DeepSeek V4.1 Flash (Max)	0.84
42	Gemini 3 Flash Preview (Non-reasoning)	0.84
44	Phi-4 Mini Instruct	0.85
44	Qwen3.5 4B (Reasoning)	0.85
46	GPT-4.1	0.86
46	MiniMax-M3.1-Flash	0.86
46	Mistral Small 4 (Non-reasoning)	0.86
46	Nemotron 3 Nano Omni 30B A3B Reasoning	0.86
50	GPT-6 Sol (Non-reasoning)	0.87