Benchmarks / Artificial Analysis

Reported by Artificial Analysis

Artificial Analysis

Median tokens a second while the model writes its answer, measured by Artificial Analysis on the model's usual API over the past weeks.

Last updated 8 Oct 2026

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

Output speed: Qwen3-Next-80B-A3B-Instruct

Top 15 of 133 results · tokens per second, higher is better. Choose a model to highlight it.Clear highlight

  1. 1 Trinity Large ThinkingArcee AI 347
  2. 2 Gemini 3.5 Flash-LiteGoogle 335
  3. 3 Nova Micro 1.0Amazon 262
  4. 4 gpt-oss-20b (low reasoning)OpenAI 255
  5. 5 Claude Haiku 5.5 (max reasoning)Anthropic 235
  6. 6 Ministral 3 3BMistral AI 233
  7. 7 Qwen3.5-Omni-FlashAlibaba 226
  8. 8 Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA 223
  9. 9 DeepSeek-V4.1-Flash (max reasoning)DeepSeek 217
  10. 9 Nova 2 Lite (no reasoning)Amazon 217
  11. 11 DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek 215
  12. 12 Nova 2 Lite (low reasoning)Amazon 210
  13. 13 DeepSeek-V4.1-Flash (no reasoning)DeepSeek 209
  14. 14 gpt-oss-20b (high reasoning)OpenAI 205
  15. 15 Nova 2 Lite (high reasoning)Amazon 203
  16. 21 Qwen3-Next-80B-A3B-InstructAlibaba 179

Full results

Artificial Analysis: Output speed, tokens per second, higher is better
#ModelOutput speed
tokens per second, higher is better		Price
$ per million tokens, in / out
1 Trinity Large ThinkingArcee AI
347
$0.25 / $0.80
2 Gemini 3.5 Flash-LiteGoogle
335
$0.30 / $2.50
3 Nova Micro 1.0Amazon
262
$0.035 / $0.14
4 gpt-oss-20b (low reasoning)OpenAI
255
$0.03 / $0.15
5 Claude Haiku 5.5 (max reasoning)Anthropic
235
$0.10 / $0.50
6 Ministral 3 3BMistral AI
233
$0.10 / $0.10
7 Qwen3.5-Omni-FlashAlibaba
226
–
8 Nemotron 3 Nano 30B A3B (no reasoning)NVIDIA
223
$0.05 / $0.20
9 DeepSeek-V4.1-Flash (max reasoning)DeepSeek
217
$0.30 / $1.20
9 Nova 2 Lite (no reasoning)Amazon
217
$0.30 / $2.50
11 DeepSeek-V4-Flash-Vision-Exp (max reasoning)DeepSeek
215
$0.44 / $1.32
12 Nova 2 Lite (low reasoning)Amazon
210
$0.30 / $2.50
13 DeepSeek-V4.1-Flash (no reasoning)DeepSeek
209
$0.30 / $1.20
14 gpt-oss-20b (high reasoning)OpenAI
205
$0.03 / $0.15
15 Nova 2 Lite (high reasoning)Amazon
203
$0.30 / $2.50
15 Claude Haiku 5.5 (extra-high reasoning)Anthropic
203
$0.10 / $0.50
17 Nova 2 Lite (medium reasoning)Amazon
199
$0.30 / $2.50
18 Nemotron 3 Nano 30B A3B (reasoning on)NVIDIA
198
$0.05 / $0.20
19 gpt-oss-120b (low reasoning)OpenAI
188
$0.15 / $0.60
20 gpt-oss-120b (high reasoning)OpenAI
183
$0.15 / $0.60
21 Qwen3-Next-80B-A3B-InstructAlibaba
179
$0.10 / $1.10
22 Qwen3-Next-80B-A3B-ThinkingAlibaba
178
$0.15 / $1.20
23 Inkling SmallThinking Machines
173
$0.45 / $1.20
24 Mistral Small 4Mistral AI
164
$0.15 / $0.60
25 Claude Haiku 5.5 (low reasoning)Anthropic
162
$0.10 / $0.50
26 Mistral Medium 3.5Mistral AI
160
$1.50 / $7.50
27 Mistral Small 4 (no reasoning)Mistral AI
153
$0.15 / $0.60
27 Inkling (extra-high reasoning)Thinking Machines
153
$0.95 / $4.05
29 Nemotron 3 Super 120B A12BNVIDIA
148
$0.085 / $0.40
30 Claude Haiku 5.5 (medium reasoning)Anthropic
147
$0.10 / $0.50
30 Gemini 3.8 Flash (high reasoning)Google
147
$1.50 / $7.50
30 Qwen3.5-122B-A10B (no reasoning)Alibaba
147
$0.26 / $2.08
33 Gemma 4 12BGoogle
146
–
34 Claude Haiku 5.5 (high reasoning)Anthropic
143
$0.10 / $0.50
35 Qwen3.6-35B-A3B (no reasoning)Alibaba
138
$0.10 / $1
35 Gemma 4 12B (no reasoning)Google
138
–
37 Claude Sonnet 5.5 (max reasoning)Anthropic
134
$2 / $10
38 Qwen3.5-122B-A10BAlibaba
132
$0.26 / $2.08
39 Qwen3.6-35B-A3BAlibaba
131
$0.10 / $1
40 GPT-6 Luna (max reasoning)OpenAI
127
$0.10 / $0.50
41 GPT-6 Luna (extra-high reasoning)OpenAI
123
$0.10 / $0.50
41 o3OpenAI
123
$2 / $8
43 Gemini 3.1 Pro PreviewGoogle
120
$2 / $12
44 GPT-6 Luna (low reasoning)OpenAI
119
$0.10 / $0.50
45 GPT-6 Luna (high reasoning)OpenAI
118
$0.10 / $0.50
46 GPT-6 Luna (no reasoning)OpenAI
116
$0.10 / $0.50
46 GPT-5.5 Instant (2026-06-26)OpenAI
116
–
48 Muse Spark 1.3 (extra-high reasoning)Meta
114
$1.25 / $4.25
49 Qwen3-Omni-30B-A3B-ThinkingAlibaba
112
–
50 Qwen3-Omni-30B-A3B-InstructAlibaba
108
–
51 Mistral Large 4Mistral AI
106
$1.36 / $4.18
51 DeepSeek-V4-Pro (0813, no reasoning)DeepSeek
106
$1.32 / $3.96
53 Muse Spark 1.3 (max reasoning)Meta
103
$1.25 / $4.25
54 Ministral 3 8BMistral AI
102
$0.15 / $0.15
55 Qwen3.5-Omni-PlusAlibaba
101
–
56 GPT-5.6 Terra (max reasoning)OpenAI
99.1
$2 / $12
57 Claude Opus 5.5 (max reasoning)Anthropic
97.4
$4 / $20
58 Claude Haiku 4.5 (reasoning on)Anthropic
97.2
$1 / $5
59 Claude Haiku 4.5 (no reasoning)Anthropic
96.8
$1 / $5
60 DeepSeek-V4-Pro (0813, max reasoning)DeepSeek
95.0
$1.32 / $3.96
61 Reka Flash 3Reka AI
94.9
$0.10 / $0.20
62 Claude Sonnet 5.5 (medium reasoning)Anthropic
94.1
$2 / $10
62 Qwen3-Coder-NextAlibaba
94.1
$0.18 / $0.90
64 Claude Sonnet 5.5 (extra-high reasoning)Anthropic
93.4
$2 / $10
65 Claude Sonnet 5.5 (high reasoning)Anthropic
92.3
$2 / $10
66 GPT-5.6 Terra (no reasoning)OpenAI
91.2
$2 / $12
67 Gemma 4 26B A4B (no reasoning)Google
90.7
$0.10 / $0.30
68 Claude Sonnet 5.5 (low reasoning)Anthropic
90.6
$2 / $10
69 Qwen3.5-397B-A17BAlibaba
90.0
$0.55 / $3.50
70 GPT-5.3-Codex (extra-high reasoning)OpenAI
89.2
$1.75 / $14
71 Hy3Tencent
87.5
$0.14 / $0.58
72 GPT-5.6 Terra (medium reasoning)OpenAI
85.2
$2 / $12
73 Qwen3.5-397B-A17B (no reasoning)Alibaba
84.9
$0.55 / $3.50
74 Llama 3.3 70B InstructMeta
84.6
$0.59 / $0.79
75 GPT-5.6 Terra (high reasoning)OpenAI
84.5
$2 / $12
76 Qwen3.5-9B (no reasoning)Alibaba
84.3
$0.10 / $0.15
77 GPT-5.6 Terra (low reasoning)OpenAI
84.1
$2 / $12
78 GPT-5.6 Terra (extra-high reasoning)OpenAI
83.9
$2 / $12
79 Kimi K2.7 CodeMoonshot AI
83.2
$0.95 / $4
80 MiniMax-M3MiniMax
82.0
$0.30 / $1.20
81 Solar Pro 4Upstage
81.6
$0.09 / $0.36
82 Ministral 3 14BMistral AI
81.3
$0.20 / $0.20
83 Muse Glimmer (high reasoning)Meta
80.4
–
84 Mistral Large 3Mistral AI
78.0
$0.50 / $1.50
85 GLM-5.3 (low reasoning)Z.ai
76.3
$1.40 / $4.40
86 Claude Opus 5.5 (extra-high reasoning)Anthropic
75.9
$4 / $20
87 GLM-5.3 (max reasoning)Z.ai
75.0
$1.40 / $4.40
88 Claude Opus 5.5 (high reasoning)Anthropic
72.4
$4 / $20
89 Claude Opus 5.5 (low reasoning)Anthropic
71.2
$4 / $20
90 Claude Opus 5.5 (medium reasoning)Anthropic
70.2
$4 / $20
91 Claude Fable 5.1 (max reasoning)Anthropic
67.1
$10 / $50
92 Grok 4.7 (high reasoning)xAI
63.7
$2 / $6
93 Grok 4.7 (low reasoning)xAI
61.8
$2 / $6
94 Grok 4.7 (extra-high reasoning)xAI
61.1
$2 / $6
95 Command ACohere
59.7
$2.50 / $10
95 Qwen3.5-9BAlibaba
59.7
$0.10 / $0.15
97 Qwen3.7-PlusAlibaba
55.4
$0.32 / $1.28
98 GPT-6.1 Sol (max reasoning)OpenAI
55.2
$2 / $10
99 Qwen3.8-Flash-NextAlibaba
54.9
–
100 GPT-6.1 Sol (extra-high reasoning)OpenAI
54.8
$2 / $10
101 MiMo-V2.6-FlashXiaomi
52.4
$0.14 / $0.28
102 Qwen3.8-27B (low reasoning)Alibaba
51.9
$0.50 / $3
102 Qwen3.8-27B (no reasoning)Alibaba
51.9
$0.50 / $3
104 GPT-6.1 Sol (low reasoning)OpenAI
51.8
$2 / $10
105 GPT-6 Astra (extra-high reasoning)OpenAI
51.7
$10 / $50
106 Granite 4.2 8BIBM
51.6
$0.06 / $0.25
107 Claude Fable 5.1 (extra-high reasoning)Anthropic
51.0
$10 / $50
107 GPT-6.1 Sol (medium reasoning)OpenAI
51.0
$2 / $10
109 GPT-6.1 Sol (high reasoning)OpenAI
50.9
$2 / $10
110 GLM-5.3-FlashZ.ai
49.5
$0.15 / $0.50
110 Claude Fable 5.1 (high reasoning)Anthropic
49.5
$10 / $50
112 Claude Fable 5.1 (low reasoning)Anthropic
49.4
$10 / $50
113 Qwen3.8-27B (medium reasoning)Alibaba
49.1
$0.50 / $3
114 GPT-6 Astra (max reasoning)OpenAI
48.0
$10 / $50
115 Claude Fable 5.1 (medium reasoning)Anthropic
47.7
$10 / $50
116 GPT-6 Astra (medium reasoning)OpenAI
47.4
$10 / $50
117 Qwen3.8-27B (extra-high reasoning)Alibaba
46.9
$0.50 / $3
118 GPT-6 Astra (high reasoning)OpenAI
46.8
$10 / $50
119 GPT-6 Astra (low reasoning)OpenAI
46.0
$10 / $50
120 Llama 4 ScoutMeta
45.6
$0.18 / $0.59
121 Kimi K3 (max reasoning)Moonshot AI
45.0
$3 / $15
122 Phi-4Microsoft
43.7
$0.07 / $0.14
123 Gemma 4 31B (no reasoning)Google
42.9
$0.14 / $0.40
124 Kimi K3 (low reasoning)Moonshot AI
41.8
$3 / $15
125 MiMo-V2.6-ProXiaomi
39.0
$0.43 / $0.87
126 Qwen3.8-2.4T-A95BAlibaba
37.5
$2 / $6
127 Qwen3.8-Max (0902)Alibaba
37.0
$2 / $6
128 Gemma 4 31BGoogle
35.0
$0.14 / $0.40
129 Llama 4 MaverickMeta
32.8
$0.27 / $0.85
130 Gemma 4 E4BGoogle
27.3
–
131 Gemma 4 E4B (no reasoning)Google
26.0
–
132 Qwen3.5-4B (reasoning on)Alibaba
23.9
–
133 Qwen3.5-4B (no reasoning)Alibaba
19.8
–

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 tokens a second while the model writes its answer, measured by Artificial Analysis on the model's usual API over the past weeks.

What it does not measure

Not time spent thinking before the answer starts, or speed 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.