Benchmarks / Artificial Analysis

Reported by Artificial Analysis

Artificial Analysis

Median seconds from sending a request to the first token of the answer, including any thinking, measured by Artificial Analysis on the model's usual API.

Last updated 20 Oct 2026

Results dated
20 Oct 2026
Results
137 configurations of 78 models
Unit
seconds
Licence
Artificial Analysis commercial data licence

Time to first answer token: MiniMax M3.1 Flash

Top 15 of 137 results · seconds, lower is better · ≈ cannot be told apart from the leader. Choose a model to highlight it.Clear highlight

  1. 1≈ Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA 0.36
  2. 1≈ Command ACohere 0.36
  3. 3 Ministral 3 3BMistral AI 0.41
  4. 4 Qwen3.5-9B (no reasoning)Alibaba 0.43
  5. 4 Gemma 4 E4B (no reasoning)Google 0.43
  6. 6 Ministral 3 8BMistral AI 0.46
  7. 7 Ministral 3 14BMistral AI 0.52
  8. 8 Nova Micro 1.0Amazon 0.55
  9. 9 Mistral Small 4 (no reasoning)Mistral AI 0.57
  10. 9 Qwen3-Next-80B-A3B-InstructAlibaba 0.57
  11. 11 Gemma 4 26B A4B (no reasoning)Google 0.60
  12. 12 Llama 4 ScoutMeta 0.61
  13. 13 DeepSeek-V4.1-Flash (no reasoning)DeepSeek 0.63
  14. 14 Llama 3.3 70B InstructMeta 0.64
  15. 15 Llama 4 MaverickMeta 0.65
  16. 67 MiniMax M3.1 FlashMiniMax 13.3

Full results

Artificial Analysis: Time to first answer token, seconds, lower is better
#ModelTime to first answer token
seconds, lower is better		Price
$ per million tokens, in / out
1≈ Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA
0.36
$0.05 / $0.20
1≈ Command ACohere
0.36
$2.50 / $10
3 Ministral 3 3BMistral AI
0.41
$0.10 / $0.10
4 Qwen3.5-9B (no reasoning)Alibaba
0.43
$0.10 / $0.15
4 Gemma 4 E4B (no reasoning)Google
0.43
–
6 Ministral 3 8BMistral AI
0.46
$0.15 / $0.15
7 Ministral 3 14BMistral AI
0.52
$0.20 / $0.20
8 Nova Micro 1.0Amazon
0.55
$0.035 / $0.14
9 Mistral Small 4 (no reasoning)Mistral AI
0.57
$0.15 / $0.60
9 Qwen3-Next-80B-A3B-InstructAlibaba
0.57
$0.10 / $1.10
11 Gemma 4 26B A4B (no reasoning)Google
0.60
$0.10 / $0.30
12 Llama 4 ScoutMeta
0.61
$0.18 / $0.59
13 DeepSeek-V4.1-Flash (no reasoning)DeepSeek
0.63
$0.30 / $1.20
14 Llama 3.3 70B InstructMeta
0.64
$0.59 / $0.79
15 Llama 4 MaverickMeta
0.65
$0.27 / $0.85
16 Qwen3.5-4B (no reasoning)Alibaba
0.70
–
17 Claude Sonnet 5.5 (low reasoning)Anthropic
0.71
$2 / $10
18 GPT-5.6 Terra (no reasoning)OpenAI
0.72
$2 / $12
19 Nova 2 Lite (no reasoning)Amazon
0.73
$0.30 / $2.50
20 GPT-6 Luna (no reasoning)OpenAI
0.74
$0.10 / $0.50
21 Qwen3-Coder-NextAlibaba
0.75
$0.18 / $0.90
22 Gemma 4 31B (no reasoning)Google
0.77
$0.14 / $0.40
23 Qwen3-Omni-30B-A3B-InstructAlibaba
0.87
–
24 Claude Sonnet 5.5 (medium reasoning)Anthropic
0.91
$2 / $10
25 Claude Fable 5.1 (low reasoning)Anthropic
0.92
$10 / $50
26 Qwen3.5-Omni-FlashAlibaba
0.94
–
27 Qwen3.5-122B-A10B (no reasoning)Alibaba
0.99
$0.26 / $2.08
28 Phi-4Microsoft
1.03
$0.07 / $0.14
29 Qwen3.6-35B-A3B (no reasoning)Alibaba
1.09
$0.10 / $1
30 Gemma 4 12B (no reasoning)Google
1.15
–
30 Qwen3.5-Omni-PlusAlibaba
1.15
–
32 DeepSeek-V4-Pro (0813, no reasoning)DeepSeek
1.18
$1.32 / $3.96
33 Qwen3.8-27B (no reasoning)Alibaba
1.27
$0.50 / $3
34 GPT-5.6 Terra (low reasoning)OpenAI
1.41
$2 / $12
34 GPT-6 Astra (low reasoning)OpenAI
1.41
$10 / $50
36 Qwen3.5-397B-A17B (no reasoning)Alibaba
1.54
$0.55 / $3.50
37 GPT-6.1 Sol (low reasoning)OpenAI
1.71
$2 / $10
38 GPT-5.6 Terra (medium reasoning)OpenAI
1.85
$2 / $12
39 GPT-6 Luna (low reasoning)OpenAI
3.52
$0.10 / $0.50
40 Grok 4.7 (low reasoning)xAI
4.00
$2 / $6
41 o3OpenAI
4.60
$2 / $8
42 Gemini 3.5 Flash-LiteGoogle
4.69
$0.30 / $2.50
43 Nemotron 3.5 Super VLNVIDIA
5.43
–
44 GPT-6 Astra (medium reasoning)OpenAI
5.71
$10 / $50
45 Claude Fable 5.1 (medium reasoning)Anthropic
6.03
$10 / $50
46 GPT-5.6 Terra (high reasoning)OpenAI
6.26
$2 / $12
47 Claude Haiku 5.5 (low reasoning)Anthropic
6.41
$0.10 / $0.50
48 Trinity Large ThinkingArcee AI
6.63
$0.25 / $0.80
49 Beam 1.0 501B A23BReflection
6.73
–
50 Claude Opus 5.5 (low reasoning)Anthropic
6.89
$4 / $20
51 GPT-6.1 Sol (medium reasoning)OpenAI
6.99
$2 / $10
52 gpt-oss-20b (low reasoning)OpenAI
7.62
$0.03 / $0.15
53 gpt-oss-20b (high reasoning)OpenAI
8.01
$0.03 / $0.15
54 gpt-oss-120b (high reasoning)OpenAI
8.22
$0.15 / $0.60
55 gpt-oss-120b (low reasoning)OpenAI
8.27
$0.15 / $0.60
56 Nemotron 3 Nano 30B A3B (reasoning on)NVIDIA
8.85
$0.05 / $0.20
57 Claude Haiku 5.5 (medium reasoning)Anthropic
8.92
$0.10 / $0.50
58 Claude Sonnet 5.5 (high reasoning)Anthropic
9.16
$2 / $10
59 DeepSeek-V4.1-Flash (max reasoning)DeepSeek
9.37
$0.30 / $1.20
60 Claude Fable 5.1 (high reasoning)Anthropic
9.98
$10 / $50
61 DeepSeek-V4.1-Flash-1017 (max reasoning)DeepSeek
10.5
$0.30 / $1.20
62 Inkling (extra-high reasoning)Thinking Machines
10.9
$0.95 / $4.05
63 DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek
11.6
$0.44 / $1.32
64 Mistral Small 4Mistral AI
12.0
$0.15 / $0.60
65 Qwen3-Next-80B-A3B-ThinkingAlibaba
12.7
$0.15 / $1.20
66 Inkling SmallThinking Machines
12.9
$0.45 / $1.20
67 MiniMax M3.1 FlashMiniMax
13.3
$0.15 / $0.60
67 Mistral Medium 3.5Mistral AI
13.3
$1.50 / $7.50
69 Claude Opus 5.5 (medium reasoning)Anthropic
13.8
$4 / $20
70 GPT-5.5 Instant (2026-06-26)OpenAI
13.9
–
71 Muse Glimmer (high reasoning)Meta
14.5
–
72 MiniMax-M3MiniMax
14.6
$0.30 / $1.20
72 Muse Spark Open (extra-high reasoning)Meta
14.6
–
74 Gemini 3.1 Pro PreviewGoogle
14.7
$2 / $12
74 Gemma 4 12BGoogle
14.7
–
76 Nova 2 Lite (low reasoning)Amazon
15.5
$0.30 / $2.50
76 Gemini 3.8 Flash (high reasoning)Google
15.5
$1.50 / $7.50
78 Claude Haiku 5.5 (high reasoning)Anthropic
16.0
$0.10 / $0.50
79 Qwen3.5-122B-A10BAlibaba
16.2
$0.26 / $2.08
80 GPT-6 Luna (high reasoning)OpenAI
17.1
$0.10 / $0.50
81 Solar Pro 4Upstage
17.9
$0.09 / $0.36
82 Grok 4.7 (high reasoning)xAI
18.5
$2 / $6
83 Claude Sonnet 5.5 (extra-high reasoning)Anthropic
19.3
$2 / $10
84 Qwen3-Omni-30B-A3B-ThinkingAlibaba
19.4
–
85 GPT-5.6 Terra (extra-high reasoning)OpenAI
20.7
$2 / $12
86 DeepSeek-V4-Pro (0813, max reasoning)DeepSeek
21.9
$1.32 / $3.96
87 Grok 4.7 (extra-high reasoning)xAI
22.0
$2 / $6
88 Nova 2 Lite (high reasoning)Amazon
23.6
$0.30 / $2.50
89 Reka Flash 3Reka AI
24.8
$0.10 / $0.20
90 GLM-5.3 (low reasoning)Z.ai
25.4
$1.40 / $4.40
91 Hy3Tencent
25.8
$0.14 / $0.58
92 Claude Opus 5.5 (high reasoning)Anthropic
26.6
$4 / $20
93 Nova 2 Lite (medium reasoning)Amazon
26.7
$0.30 / $2.50
94 Magistral Small 1.2Mistral AI
27.1
–
95 GLM-5.3-FlashZ.ai
27.5
$0.15 / $0.50
96 GLM-5.3 (max reasoning)Z.ai
28.2
$1.40 / $4.40
97 Qwen3.5-9BAlibaba
29.1
$0.10 / $0.15
98 Muse Spark 1.3 (extra-high reasoning)Meta
29.6
$1.25 / $4.25
99 Granite 4.2 8BIBM
31.2
$0.06 / $0.25
100 Mistral Large 4Mistral AI
33.9
$1.36 / $4.18
101 Qwen3.7-PlusAlibaba
37.3
$0.32 / $1.28
102 Qwen3.8-Flash-NextAlibaba
37.6
–
103 GPT-6 Luna (extra-high reasoning)OpenAI
37.7
$0.10 / $0.50
104 Gemma 4 26B A4BGoogle
38.4
$0.10 / $0.30
105 GPT-6.1 Sol (high reasoning)OpenAI
41.0
$2 / $10
106 Qwen3.6-35B-A3BAlibaba
41.6
$0.10 / $1
107 Kimi K2.7 CodeMoonshot AI
42.7
$0.95 / $4
108 Qwen3.8-27B (low reasoning)Alibaba
44.4
$0.50 / $3
109 GPT-5.3-Codex (extra-high reasoning)OpenAI
44.9
$1.75 / $14
110 Claude Haiku 5.5 (extra-high reasoning)Anthropic
45.9
$0.10 / $0.50
111 Claude Fable 5.1 (extra-high reasoning)Anthropic
47.2
$10 / $50
112 MiMo-V2.6-FlashXiaomi
47.4
$0.14 / $0.28
113 Qwen3.8-27B (medium reasoning)Alibaba
47.7
$0.50 / $3
114 Muse Wonder (max reasoning)Meta
48.2
$4 / $20
115 MiMo-V2.6-ProXiaomi
49.8
$0.43 / $0.87
116 Gemma 4 31BGoogle
50.0
$0.14 / $0.40
117 GPT-6 Astra (high reasoning)OpenAI
50.6
$10 / $50
118 Kimi K3 (max reasoning)Moonshot AI
51.8
$3 / $15
119 Qwen3.8-27B (extra-high reasoning)Alibaba
52.4
$0.50 / $3
120 Kimi K3 (low reasoning)Moonshot AI
53.0
$3 / $15
121 Muse Spark 1.3 (max reasoning)Meta
56.2
$1.25 / $4.25
121 Qwen3.8-Max (0902)Alibaba
56.2
$2 / $6
123 Qwen3.8-2.4T-A95BAlibaba
58.0
$2 / $6
124 Qwen3.5-397B-A17BAlibaba
59.9
$0.55 / $3.50
125 Gemma 4 E4BGoogle
71.9
–
126 Claude Opus 5.5 (extra-high reasoning)Anthropic
80.9
$4 / $20
127 GPT-6.1 Sol (extra-high reasoning)OpenAI
110
$2 / $10
128 GPT-6 Luna (max reasoning)OpenAI
116
$0.10 / $0.50
129 GPT-6 Astra (extra-high reasoning)OpenAI
118
$10 / $50
130 Claude Fable 5.1 (max reasoning)Anthropic
169
$10 / $50
131 GPT-5.6 Terra (max reasoning)OpenAI
196
$2 / $12
132 Qwen3.5-4B (reasoning on)Alibaba
207
–
133 GPT-6 Astra (max reasoning)OpenAI
220
$10 / $50
134 GPT-6.1 Sol (max reasoning)OpenAI
255
$2 / $10
135 Claude Haiku 5.5 (max reasoning)Anthropic
279
$0.10 / $0.50
136 Claude Sonnet 5.5 (max reasoning)Anthropic
322
$2 / $10
137 Claude Opus 5.5 (max reasoning)Anthropic
621
$4 / $20

Swipe the table sideways for more columns.

Ranks follow the score as shown, so equal numbers share a rank. Results as published by Artificial Analysis; we do not re-run them.

Progress over time

Time to first answer token, plotted at each model's release date, lower is better. Each model counts once, at its best setting. Scores are today's, not launch day's. Hover or tap a mark for its model.

Best score so far

Every model at its release date. The line moves each time a new release beats every earlier one, and each new best is named where there is room.

-20020406080 2025Jul2026Jul Nova Micro 1.0Ministral 3 3BNemotron 3 Nano 30B A3B

Best score by lab

Each lab's best so far, stepping whenever one of its releases beats its own earlier models. The 6 labs with the best scores today; 17 others not drawn.

NVIDIACohereMistral AIAlibabaGoogleAmazon

-100102030 2025Jul2026Jul NVIDIACohereMistral AIAlibabaGoogleAmazon

What it measures

Median seconds from sending a request to the first token of the answer, including any thinking, measured by Artificial Analysis on the model's usual API.

What it does not measure

Not total time for a long answer, or latency on other hosts.

Source

Artificial Analysis · Methodology

285 results from Artificial Analysis not ranked here · show why

We rank a result only when we can tie it to a specific model you can use. These are left out:

  • Not on sale through the API providers we track: 270
  • A different snapshot or variant from the model we list: 14
  • An unusual combination of settings: 1

Data sourced from Artificial Analysis. Licence: Artificial Analysis commercial data licence.