LogoLMSpeed
  • Home
  • Free
  • Models
  • Providers
  • Docs
LogoLMSpeed
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
Leaderboard
  • Overview
  • Speed Ranking
  • Latency Ranking
  • Health Ranking
  • Model Pricing
  • Model Speed
  • Reasoning
  • Coding
Models
  • All Models
  • GPT
  • Claude
  • Gemini
  • DeepSeek
  • Llama
  • Qwen
Free Models
  • All Free Models
  • Free GPT
  • Free Claude
  • Free Gemini
  • Free DeepSeek
  • Free Llama
  • Free Qwen
Resources
  • Speed Test
  • Provider Directory
  • Documentation
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 LMSpeed All Rights Reserved.Made by Nexmoe with ❤️

LMSpeed Model Speed Leaderboard

Multi-dimensional rankings based on model speed tests, provider health checks, and standard model benchmarks. Compare providers, endpoints, models, and reliability at a glance.

Compares AI model responsiveness across Artificial Analysis output speed, time to first token, and time to first answer token in one table.

Updated: Jun 12, 2026, 04:00 PM·Artificial Analysis standard benchmarks

ThroughputFirst Token LatencyHealthModel PerformanceModel PricingModel Speed
Fairness Notice
These model leaderboards use imported Artificial Analysis benchmark records and are deduplicated to one canonical LMSpeed model per rank.
RankModelOutput SpeedTime to First TokenTime to First Answer TokenUpdated
1
Gemini
Gemini 3.1 Flash Litegemini-3-1-flash-lite
319.9 tok/s#1
5.31 s#61
5.31 s#40
Jun 12, 2026, 04:00 PM
2
Qwen
Qwen3.5 Omni Flashqwen3-5-omni-flash
258.1 tok/s#2
0.98 s#24
0.98 s#17
Jun 12, 2026, 04:00 PM
3
OpenAI
GPT-OSSgpt-oss
243.2 tok/s#3
0.50 s#6
8.72 s#43
Jun 12, 2026, 04:00 PM
4
Gemini
Gemini 2.5 Flash Litegemini-2-5-flash-lite
229.0 tok/s#4
0.37 s#2
0.37 s#2
Jun 12, 2026, 04:00 PM
5
OpenAI
GPT-5.1 Codex Minigpt-5-1-codex-mini
215.4 tok/s#5
3.65 s#57
3.65 s#36
Jun 12, 2026, 04:00 PM
6
Stepfun
Step 3.5 Flashstep-3-5-flash
209.9 tok/s#6
0.84 s#18
10.37 s#44
Jun 12, 2026, 04:00 PM
7
Gemini
Gemini 2.5 Flashgemini-2-5-flash
194.9 tok/s#7
0.54 s#10
0.54 s#9
Jun 12, 2026, 04:00 PM
8
Gemini
Gemini 3 Flashgemini-3-flash
190.4 tok/s#8
4.95 s#60
4.95 s#39
Jun 12, 2026, 04:00 PM
9
OpenAI
GPT-5.1 Codexgpt-5-1-codex
185.7 tok/s#9
4.25 s#59
4.25 s#38
Jun 12, 2026, 04:00 PM
10
Grok
Grok 4.20grok-4-20
178.5 tok/s#10
13.54 s#68
13.54 s#47
Jun 12, 2026, 04:00 PM
11
OpenAI
O3 Minio3-mini
175.5 tok/s#11
5.92 s#63
5.92 s#41
Jun 12, 2026, 04:00 PM
12
Ministral 3ministral-3
172.1 tok/s#12
0.33 s#1
0.33 s#1
Jun 12, 2026, 04:00 PM
13
OpenAI
GPT-5 Codexgpt-5-codex
170.0 tok/s#13
11.29 s#66
11.29 s#45
Jun 12, 2026, 04:00 PM
14
Minimax
MiniMax M2.1minimax-m2-1
169.0 tok/s#14
7.00 s#64
18.83 s#53
Jun 12, 2026, 04:00 PM
15
OpenAI
GPT-5.4 Minigpt-5-4-mini
165.0 tok/s#15
3.95 s#58
3.95 s#37
Jun 12, 2026, 04:00 PM
16
OpenAI
o4 Minio4-mini
159.9 tok/s#16
33.67 s#75
33.67 s#63
Jun 12, 2026, 04:00 PM
17
Minimax
MiniMax M2.5minimax-m2-5
157.1 tok/s#17
5.40 s#62
18.13 s#51
Jun 12, 2026, 04:00 PM
18
MiMo-V2-Flashmimo-v2-flash
154.1 tok/s#18
1.27 s#35
1.27 s#23
Jun 12, 2026, 04:00 PM
19
OpenAI
O1o1
149.7 tok/s#19
14.20 s#69
14.20 s#48
Jun 12, 2026, 04:00 PM
20
OpenAI
GPT-5.4 Nanogpt-5-4-nano
148.7 tok/s#20
2.46 s#54
2.46 s#35
Jun 12, 2026, 04:00 PM
21
OpenAI
GPT-5 Nanogpt-5-nano
142.3 tok/s#21
81.19 s#79
81.19 s#77
Jun 12, 2026, 04:00 PM
22
Qwen
Qwen3qwen3
140.3 tok/s#22
1.12 s#31
1.12 s#20
Jun 12, 2026, 04:00 PM
23
Gemini
Gemini 3.1 Progemini-3-1-pro
133.4 tok/s#23
28.68 s#73
28.68 s#61
Jun 12, 2026, 04:00 PM
24
Gemini
Gemini 2.5 Progemini-2-5-pro
132.3 tok/s#24
23.08 s#72
23.08 s#56
Jun 12, 2026, 04:00 PM
25
OpenAI
GPT-4.1gpt-4-1
129.4 tok/s#25
0.64 s#16
0.64 s#15
Jun 12, 2026, 04:00 PM
26
MoonshotAI
Kimi K2 Thinkingkimi-k2-thinking
128.6 tok/s#26
0.93 s#22
16.49 s#49
Jun 12, 2026, 04:00 PM
27
OpenAI
GPT-4ogpt-4o
125.9 tok/s#27
0.51 s#8
0.51 s#7
Jun 12, 2026, 04:00 PM
28
OpenAI
GPT-5.2 Codexgpt-5-2-codex
125.5 tok/s#28
1.17 s#32
1.17 s#21
Jun 12, 2026, 04:00 PM
29
OpenAI
GPT-4.1 Nanogpt-4-1-nano
125.3 tok/s#29
0.47 s#4
0.47 s#4
Jun 12, 2026, 04:00 PM
30
OpenAI
GPT-5.1gpt-5-1
116.2 tok/s#30
21.00 s#71
21.00 s#55
Jun 12, 2026, 04:00 PM
31
Minimax
MiniMax M2minimax-m2
114.8 tok/s#31
1.11 s#30
18.54 s#52
Jun 12, 2026, 04:00 PM
32
OpenAI
GPT-5gpt-5
109.6 tok/s#32
62.85 s#77
62.85 s#71
Jun 12, 2026, 04:00 PM
33
ChatGLM
GLM-4.7glm-4-7
107.0 tok/s#33
0.86 s#19
19.55 s#54
Jun 12, 2026, 04:00 PM
34
OpenAI
O3o3
105.6 tok/s#34
7.29 s#65
7.29 s#42
Jun 12, 2026, 04:00 PM
35
Claude
Claude Haiku 4.5claude-haiku-4-5
103.5 tok/s#35
0.90 s#21
0.90 s#16
Jun 12, 2026, 04:00 PM
36
DeepSeek
DeepSeek V4 Flashdeepseek-v4-flash
96.7 tok/s#36
0.94 s#23
58.99 s#70
Jun 12, 2026, 04:00 PM
37
MetaAI
Llama 4 Scoutllama-4-scout
92.7 tok/s#37
0.63 s#15
0.63 s#14
Jun 12, 2026, 04:00 PM
38
OpenAI
GPT-5.4gpt-5-4
92.4 tok/s#38
134.24 s#83
134.24 s#83
Jun 12, 2026, 04:00 PM
39
Mistral
Mistral Medium 3.1mistral-medium-3-1
89.5 tok/s#39
0.49 s#5
0.49 s#5
Jun 12, 2026, 04:00 PM
40
OpenAI
GPT-5 Minigpt-5-mini
83.5 tok/s#40
117.81 s#82
117.81 s#82
Jun 12, 2026, 04:00 PM
41
ChatGLM
GLM-4.5 Airglm-4-5-air
82.9 tok/s#41
1.65 s#44
25.77 s#57
Jun 12, 2026, 04:00 PM
42
MiMo-V2.5mimo-v2-5
81.3 tok/s#42
3.34 s#56
27.96 s#59
Jun 12, 2026, 04:00 PM
43
OpenAI
GPT-4.1 Minigpt-4-1-mini
80.2 tok/s#43
0.56 s#12
0.56 s#11
Jun 12, 2026, 04:00 PM
44
MiMo-V2-Omnimimo-v2-omni
79.3 tok/s#44
3.00 s#55
28.24 s#60
Jun 12, 2026, 04:00 PM
45
OpenAI
GPT-5.3 Codexgpt-5-3-codex
77.7 tok/s#45
57.06 s#76
57.06 s#68
Jun 12, 2026, 04:00 PM
46
ChatGLM
GLM-4.7 Flashglm-4-7-flash
76.3 tok/s#46
1.11 s#29
27.33 s#58
Jun 12, 2026, 04:00 PM
47
ChatGLM
GLM-5glm-5
75.5 tok/s#47
0.84 s#17
41.94 s#65
Jun 12, 2026, 04:00 PM
48
OpenAI
GPT-5.2gpt-5-2
72.8 tok/s#48
115.69 s#81
115.69 s#81
Jun 12, 2026, 04:00 PM
49
ChatGLM
GLM-5.1glm-5-1
71.0 tok/s#49
0.90 s#20
54.31 s#67
Jun 12, 2026, 04:00 PM
50
ChatGLM
GLM-4.6Vglm-4-6v
68.0 tok/s#50
1.19 s#33
1.19 s#22
Jun 12, 2026, 04:00 PM
51
Claude
Claude Fable 5claude-fable-5
63.2 tok/s#51
63.95 s#78
63.95 s#73
Jun 12, 2026, 04:00 PM
52
Mistral
Mistral Large 3mistral-large-3
62.6 tok/s#52
0.60 s#13
0.60 s#12
Jun 12, 2026, 04:00 PM
53
OpenAI
GPT-4o Minigpt-4o-mini
62.2 tok/s#53
0.53 s#9
0.53 s#8
Jun 12, 2026, 04:00 PM
54
DeepSeek
DeepSeek V4 Prodeepseek-v4-pro
57.5 tok/s#54
1.06 s#26
77.20 s#75
Jun 12, 2026, 04:00 PM
55
Claude
Claude Opus 4.8claude-opus-4-8
57.4 tok/s#55
17.66 s#70
17.66 s#50
Jun 12, 2026, 04:00 PM
56
Qwen
Qwen3.5 Omni Plusqwen3-5-omni-plus
54.8 tok/s#56
1.28 s#37
1.28 s#25
Jun 12, 2026, 04:00 PM
57
Qwen
Qwen3 Maxqwen3-max
53.9 tok/s#57
1.90 s#50
1.90 s#33
Jun 12, 2026, 04:00 PM
58
Qwen
Qwen3.6 Plusqwen3-6-plus
53.3 tok/s#58
1.83 s#48
106.03 s#79
Jun 12, 2026, 04:00 PM
59
Qwen
Qwen3.5qwen3-5
51.8 tok/s#59
1.80 s#47
63.27 s#72
Jun 12, 2026, 04:00 PM
60
ChatGLM
GLM-4.6glm-4-6
51.7 tok/s#60
1.74 s#46
1.74 s#31
Jun 12, 2026, 04:00 PM
61
Claude
Claude Opus 4.5claude-opus-4-5
50.4 tok/s#61
1.31 s#38
1.31 s#26
Jun 12, 2026, 04:00 PM
62
ChatGLM
GLM-4.5glm-4-5
49.9 tok/s#62
1.01 s#25
41.05 s#64
Jun 12, 2026, 04:00 PM
63
Claude
Claude Sonnet 4claude-sonnet-4
49.5 tok/s#63
1.07 s#27
1.07 s#18
Jun 12, 2026, 04:00 PM
64
Devstral Smalldevstral-small
49.1 tok/s#64
0.55 s#11
0.55 s#10
Jun 12, 2026, 04:00 PM
65
Claude
Claude Sonnet 4.5claude-sonnet-4-5
47.9 tok/s#65
1.55 s#42
1.55 s#29
Jun 12, 2026, 04:00 PM
66
MoonshotAI
Kimi K2.5kimi-k2-5
47.1 tok/s#66
1.27 s#34
64.24 s#74
Jun 12, 2026, 04:00 PM
67
Claude
Claude Sonnet 4.6claude-sonnet-4-6
47.0 tok/s#67
1.28 s#36
1.28 s#24
Jun 12, 2026, 04:00 PM
68
Claude
Claude Opus 4.7claude-opus-4-7
46.9 tok/s#68
11.41 s#67
11.41 s#46
Jun 12, 2026, 04:00 PM
69
Claude
Claude Opus 4.6claude-opus-4-6
44.9 tok/s#69
1.44 s#40
1.44 s#27
Jun 12, 2026, 04:00 PM
70
Minimax
MiniMax M2.7minimax-m2-7
43.5 tok/s#70
1.59 s#43
58.23 s#69
Jun 12, 2026, 04:00 PM
71
ChatGLM
GLM-4.5Vglm-4-5v
43.2 tok/s#71
32.30 s#74
32.30 s#62
Jun 12, 2026, 04:00 PM
72
Phi 4phi-4
42.7 tok/s#72
0.50 s#6
0.50 s#6
Jun 12, 2026, 04:00 PM
73
MoonshotAI
Kimi K2.6kimi-k2-6
40.5 tok/s#73
1.37 s#39
111.36 s#80
Jun 12, 2026, 04:00 PM
74
OpenAI
GPT-4gpt-4
39.3 tok/s#74
1.07 s#28
1.07 s#19
Jun 12, 2026, 04:00 PM
75
MiMo-V2.5-Promimo-v2-5-pro
38.7 tok/s#75
2.13 s#52
53.87 s#66
Jun 12, 2026, 04:00 PM
76
MiMo-V2-Promimo-v2-pro
37.1 tok/s#76
2.17 s#53
80.97 s#76
Jun 12, 2026, 04:00 PM
77
Claude
Claude Opus 4.1claude-opus-4-1
36.8 tok/s#77
1.98 s#51
1.98 s#34
Jun 12, 2026, 04:00 PM
78
Claude
Claude Opus 4claude-opus-4
36.6 tok/s#78
1.87 s#49
1.87 s#32
Jun 12, 2026, 04:00 PM
79
Devstral 2devstral-2
33.4 tok/s#79
0.61 s#14
0.61 s#13
Jun 12, 2026, 04:00 PM
80
MetaAI
Hermes 3 Llama 3.1hermes-3-llama-3-1
32.4 tok/s#80
0.37 s#2
0.37 s#2
Jun 12, 2026, 04:00 PM
81
OpenAI
GPT-4 Turbogpt-4-turbo
26.6 tok/s#81
1.66 s#45
1.66 s#30
Jun 12, 2026, 04:00 PM
82
MoonshotAI
Kimi K2kimi-k2
23.5 tok/s#82
1.54 s#41
1.54 s#28
Jun 12, 2026, 04:00 PM
83
OpenAI
o3 Proo3-pro
20.3 tok/s#83
83.81 s#80
83.81 s#78
Jun 12, 2026, 04:00 PM
Throughputt/s
First Token Latencys
HealthAvg probe latency
Model PerformanceAA benchmark matrix
Model PricingAA pricing matrix
Model
Provider