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 8 Oct 2026

Results dated
8 Oct 2026
Results
133 configurations of 74 models
Unit
seconds
Licence
Artificial Analysis commercial data licence

Time to first answer token: Claude Haiku 5.5

Top 15 of 133 results · seconds, lower is better. Choose a model to highlight it.Clear highlight

  1. 1 Command ACohere 0.40
  2. 2 Gemma 4 E4B (no reasoning)Google 0.41
  3. 3 Claude Haiku 4.5 (no reasoning)Anthropic 0.42
  4. 4 Qwen3.5-9B (no reasoning)Alibaba 0.43
  5. 5 Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA 0.45
  6. 6 Mistral Small 4 (no reasoning)Mistral AI 0.47
  7. 7 Ministral 3 8BMistral AI 0.49
  8. 8 Ministral 3 14BMistral AI 0.51
  9. 9 Ministral 3 3BMistral AI 0.54
  10. 10 Nova Micro 1.0Amazon 0.60
  11. 11 Llama 4 ScoutMeta 0.62
  12. 12 Llama 3.3 70B InstructMeta 0.64
  13. 13 Llama 4 MaverickMeta 0.66
  14. 13 Gemma 4 26B A4B (no reasoning)Google 0.66
  15. 15 Mistral Large 3Mistral AI 0.69
  16. 50 Claude Haiku 5.5 (low reasoning)Anthropic 5.08
  17. 58 Claude Haiku 5.5 (medium reasoning)Anthropic 8.09
  18. 83 Claude Haiku 5.5 (high reasoning)Anthropic 18.8
  19. 120 Claude Haiku 5.5 (extra-high reasoning)Anthropic 63.5
  20. 132 Claude Haiku 5.5 (max reasoning)Anthropic 334

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 Command ACohere
0.40
$2.50 / $10
2 Gemma 4 E4B (no reasoning)Google
0.41
–
3 Claude Haiku 4.5 (no reasoning)Anthropic
0.42
$1 / $5
4 Qwen3.5-9B (no reasoning)Alibaba
0.43
$0.10 / $0.15
5 Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA
0.45
$0.05 / $0.20
6 Mistral Small 4 (no reasoning)Mistral AI
0.47
$0.15 / $0.60
7 Ministral 3 8BMistral AI
0.49
$0.15 / $0.15
8 Ministral 3 14BMistral AI
0.51
$0.20 / $0.20
9 Ministral 3 3BMistral AI
0.54
$0.10 / $0.10
10 Nova Micro 1.0Amazon
0.60
$0.035 / $0.14
11 Llama 4 ScoutMeta
0.62
$0.18 / $0.59
12 Llama 3.3 70B InstructMeta
0.64
$0.59 / $0.79
13 Llama 4 MaverickMeta
0.66
$0.27 / $0.85
13 Gemma 4 26B A4B (no reasoning)Google
0.66
$0.10 / $0.30
15 Mistral Large 3Mistral AI
0.69
$0.50 / $1.50
16 Qwen3.5-4B (no reasoning)Alibaba
0.71
–
17 Claude Sonnet 5.5 (medium reasoning)Anthropic
0.76
$2 / $10
17 GPT-5.6 Terra (no reasoning)OpenAI
0.76
$2 / $12
19 GPT-6 Luna (no reasoning)OpenAI
0.82
$0.10 / $0.50
20 Gemma 4 31B (no reasoning)Google
0.83
$0.14 / $0.40
21 DeepSeek-V4.1-Flash (no reasoning)DeepSeek
0.85
$0.30 / $1.20
22 Claude Sonnet 5.5 (low reasoning)Anthropic
0.87
$2 / $10
23 Nova 2 Lite (no reasoning)Amazon
0.90
$0.30 / $2.50
24 DeepSeek-V4-Pro (0813, no reasoning)DeepSeek
0.92
$1.32 / $3.96
25 Qwen3-Omni-30B-A3B-InstructAlibaba
0.94
–
26 Qwen3-Coder-NextAlibaba
0.97
$0.18 / $0.90
27 Qwen3.5-Omni-FlashAlibaba
0.98
–
28 Phi-4Microsoft
1.01
$0.07 / $0.14
29 Qwen3.6-35B-A3B (no reasoning)Alibaba
1.04
$0.10 / $1
30 Qwen3.5-122B-A10B (no reasoning)Alibaba
1.05
$0.26 / $2.08
31 Qwen3-Next-80B-A3B-InstructAlibaba
1.08
$0.10 / $1.10
32 Qwen3.8-27B (no reasoning)Alibaba
1.19
$0.50 / $3
33 GPT-5.6 Terra (low reasoning)OpenAI
1.21
$2 / $12
34 Qwen3.5-Omni-PlusAlibaba
1.24
–
35 Gemma 4 12B (no reasoning)Google
1.41
–
35 GPT-5.6 Terra (medium reasoning)OpenAI
1.41
$2 / $12
37 Qwen3.5-397B-A17B (no reasoning)Alibaba
1.59
$0.55 / $3.50
38 Claude Opus 5.5 (low reasoning)Anthropic
1.69
$4 / $20
38 GPT-6.1 Sol (low reasoning)OpenAI
1.69
$2 / $10
40 GPT-6 Luna (low reasoning)OpenAI
1.91
$0.10 / $0.50
41 GPT-5.6 Terra (high reasoning)OpenAI
2.05
$2 / $12
42 GPT-6 Astra (low reasoning)OpenAI
2.11
$10 / $50
43 Claude Fable 5.1 (low reasoning)Anthropic
2.22
$10 / $50
44 Claude Fable 5.1 (medium reasoning)Anthropic
2.96
$10 / $50
45 GPT-6 Astra (medium reasoning)OpenAI
3.38
$10 / $50
46 Grok 4.7 (low reasoning)xAI
3.44
$2 / $6
47 Claude Fable 5.1 (high reasoning)Anthropic
3.64
$10 / $50
48 GPT-6.1 Sol (medium reasoning)OpenAI
4.26
$2 / $10
49 GPT-5.6 Terra (extra-high reasoning)OpenAI
4.45
$2 / $12
50 Claude Haiku 5.5 (low reasoning)Anthropic
5.08
$0.10 / $0.50
51 o3OpenAI
5.41
$2 / $8
52 Grok 4.7 (high reasoning)xAI
5.57
$2 / $6
53 Claude Haiku 4.5 (reasoning on)Anthropic
6.04
$1 / $5
54 Claude Sonnet 5.5 (high reasoning)Anthropic
6.20
$2 / $10
55 Trinity Large ThinkingArcee AI
6.85
$0.25 / $0.80
56 Gemini 3.5 Flash-LiteGoogle
7.29
$0.30 / $2.50
57 Grok 4.7 (extra-high reasoning)xAI
7.72
$2 / $6
58 Claude Haiku 5.5 (medium reasoning)Anthropic
8.09
$0.10 / $0.50
59 gpt-oss-20b (low reasoning)OpenAI
8.30
$0.03 / $0.15
60 GPT-6 Luna (high reasoning)OpenAI
9.64
$0.10 / $0.50
61 DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek
10.1
$0.44 / $1.32
61 DeepSeek-V4.1-Flash (max reasoning)DeepSeek
10.1
$0.30 / $1.20
63 gpt-oss-20b (high reasoning)OpenAI
10.2
$0.03 / $0.15
64 Nemotron 3 Nano 30B A3B (reasoning on)NVIDIA
10.7
$0.05 / $0.20
65 Claude Sonnet 5.5 (extra-high reasoning)Anthropic
11.1
$2 / $10
66 gpt-oss-120b (low reasoning)OpenAI
11.2
$0.15 / $0.60
67 gpt-oss-120b (high reasoning)OpenAI
11.4
$0.15 / $0.60
68 Qwen3-Next-80B-A3B-ThinkingAlibaba
12.4
$0.15 / $1.20
69 Claude Opus 5.5 (medium reasoning)Anthropic
12.5
$4 / $20
70 Mistral Small 4Mistral AI
12.8
$0.15 / $0.60
71 Mistral Medium 3.5Mistral AI
13.1
$1.50 / $7.50
72 Nova 2 Lite (low reasoning)Amazon
13.3
$0.30 / $2.50
73 Inkling SmallThinking Machines
13.9
$0.45 / $1.20
74 Nemotron 3 Super 120B A12BNVIDIA
14.3
$0.085 / $0.40
75 Gemini 3.8 Flash (high reasoning)Google
14.7
$1.50 / $7.50
76 Gemma 4 12BGoogle
15.1
–
77 Claude Opus 5.5 (high reasoning)Anthropic
15.2
$4 / $20
78 Inkling (extra-high reasoning)Thinking Machines
15.4
$0.95 / $4.05
79 Qwen3.5-122B-A10BAlibaba
16.2
$0.26 / $2.08
80 Gemini 3.1 Pro PreviewGoogle
16.5
$2 / $12
81 GPT-6 Luna (extra-high reasoning)OpenAI
16.8
$0.10 / $0.50
82 GPT-5.5 Instant (2026-06-26)OpenAI
18.1
–
83 Claude Haiku 5.5 (high reasoning)Anthropic
18.8
$0.10 / $0.50
84 Qwen3-Omni-30B-A3B-ThinkingAlibaba
18.9
–
85 Nova 2 Lite (high reasoning)Amazon
19.2
$0.30 / $2.50
86 Nova 2 Lite (medium reasoning)Amazon
19.5
$0.30 / $2.50
87 Mistral Large 4Mistral AI
19.8
$1.36 / $4.18
88 GPT-6.1 Sol (high reasoning)OpenAI
20.4
$2 / $10
89 Reka Flash 3Reka AI
21.9
$0.10 / $0.20
90 DeepSeek-V4-Pro (0813, max reasoning)DeepSeek
22.2
$1.32 / $3.96
91 Hy3Tencent
24.8
$0.14 / $0.58
92 MiniMax-M3MiniMax
25.2
$0.30 / $1.20
93 Solar Pro 4Upstage
25.5
$0.09 / $0.36
94 Muse Glimmer (high reasoning)Meta
25.6
–
95 GPT-6 Astra (high reasoning)OpenAI
26.9
$10 / $50
96 Kimi K2.7 CodeMoonshot AI
27.9
$0.95 / $4
97 GLM-5.3 (low reasoning)Z.ai
29.0
$1.40 / $4.40
98 GLM-5.3 (max reasoning)Z.ai
29.8
$1.40 / $4.40
99 Qwen3.5-9BAlibaba
34.5
$0.10 / $0.15
100 Claude Fable 5.1 (extra-high reasoning)Anthropic
36.7
$10 / $50
101 GPT-5.3-Codex (extra-high reasoning)OpenAI
36.9
$1.75 / $14
102 Qwen3.5-397B-A17BAlibaba
37.0
$0.55 / $3.50
103 Qwen3.7-PlusAlibaba
37.8
$0.32 / $1.28
104 Qwen3.8-Flash-NextAlibaba
38.0
–
105 Granite 4.2 8BIBM
39.1
$0.06 / $0.25
106 Qwen3.8-27B (low reasoning)Alibaba
39.7
$0.50 / $3
107 Qwen3.8-27B (medium reasoning)Alibaba
42.0
$0.50 / $3
108 MiMo-V2.6-FlashXiaomi
42.2
$0.14 / $0.28
109 Qwen3.6-35B-A3BAlibaba
42.3
$0.10 / $1
110 GLM-5.3-FlashZ.ai
43.3
$0.15 / $0.50
111 Qwen3.8-27B (extra-high reasoning)Alibaba
43.8
$0.50 / $3
112 Muse Spark 1.3 (extra-high reasoning)Meta
45.4
$1.25 / $4.25
113 Muse Spark 1.3 (max reasoning)Meta
46.2
$1.25 / $4.25
114 Kimi K3 (max reasoning)Moonshot AI
47.3
$3 / $15
115 Gemma 4 31BGoogle
50.5
$0.14 / $0.40
116 Kimi K3 (low reasoning)Moonshot AI
50.7
$3 / $15
117 Qwen3.8-2.4T-A95BAlibaba
55.0
$2 / $6
118 MiMo-V2.6-ProXiaomi
55.8
$0.43 / $0.87
118 Qwen3.8-Max (0902)Alibaba
55.8
$2 / $6
120 Claude Haiku 5.5 (extra-high reasoning)Anthropic
63.5
$0.10 / $0.50
121 GPT-6.1 Sol (extra-high reasoning)OpenAI
65.6
$2 / $10
122 GPT-6 Luna (max reasoning)OpenAI
67.7
$0.10 / $0.50
123 Claude Opus 5.5 (extra-high reasoning)Anthropic
71.3
$4 / $20
124 Gemma 4 E4BGoogle
73.9
–
125 GPT-5.6 Terra (max reasoning)OpenAI
81.8
$2 / $12
126 Qwen3.5-4B (reasoning on)Alibaba
84.4
–
127 GPT-6 Astra (extra-high reasoning)OpenAI
85.8
$10 / $50
128 Claude Fable 5.1 (max reasoning)Anthropic
150
$10 / $50
129 GPT-6.1 Sol (max reasoning)OpenAI
183
$2 / $10
130 GPT-6 Astra (max reasoning)OpenAI
236
$10 / $50
131 Claude Sonnet 5.5 (max reasoning)Anthropic
269
$2 / $10
132 Claude Haiku 5.5 (max reasoning)Anthropic
334
$0.10 / $0.50
133 Claude Opus 5.5 (max reasoning)Anthropic
518
$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.

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

282 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: 268
  • A different snapshot or variant from the model we list: 13
  • An unusual combination of settings: 1

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