Models tracked
—
Across the selected period
Community telemetry
See how models perform in the real world.
Usage, speed, value, and intelligence scores—grounded in how CodingFleet users actually work, not marketing claims.
Tokens served
—
Prompt and completion tokens
Fastest response
—
Output tokens per second
Community favorite
—
Models with 10+ votes
Token usage over time
Model usage across CodingFleet.
Loading usage data…
Model leaderboard
Sort any metric, then narrow the list without reloading.
| Model | Speed | Usage | Credits | User score | Intelligence |
|---|---|---|---|---|---|
1
DeepSeek V4 Pro
|
82.4 tok/s | 14.0B | 2–3.5 | 0.6 | 36.0 |
|
2
DeepSeek V4 Flash
|
155.1 tok/s | 13.5B | 1 | 0.8 | 34.3 |
|
3
DeepSeek V4.1 Flash
|
175.9 tok/s | 8.7B | 1 Unlimited | 0.9 | 39.5 |
4
GPT-5.6 Luna
|
81.8 tok/s | 8.7B | 0.5–0.9 Unlimited | 0.5 | 37.3 |
5
Claude Haiku 4.5
|
115.4 tok/s | 5.2B | 2–3 | 0.1 | — |
|
6
Claude Sonnet 4.5
|
56.0 tok/s | 4.6B | 7–8 | 0.5 | — |
|
7
Claude Sonnet 4.6
|
57.1 tok/s | 3.2B | 9–10 | 1.0 | 24.7 |
|
8
GPT-5.2
|
47.7 tok/s | 2.9B | 4–8 | 0.8 | 30.4 |
|
9
Claude Opus 4.6
|
48.4 tok/s | 2.6B | 15–17 | 1.0 | 26.4 |
|
10
GPT-5.6 Terra
|
71.5 tok/s | 2.5B | 5–7.5 | 0.8 | 42.1 |
|
11
GPT-5.4
|
65.2 tok/s | 2.3B 1 | 8–12 | 0.9 | 39.0 |
|
12
GPT-5 Mini
|
63.7 tok/s | 2.1B 1 | 1–2 | 0.7 | 25.8 |
13
Gemini 3 Flash
|
141.3 tok/s | 2.1B | 1 | 0.2 | 17.9 |
|
14
GPT-6 Luna
|
92.4 tok/s | 2.0B | 0.2–0.6 Unlimited | — | 37.3 |
|
15
Claude Opus 4.5
|
57.0 tok/s | 2.0B | 15–17 | — | 29.1 |
|
16
Claude Sonnet 5
|
89.6 tok/s | 2.0B | 6.8–10 | — | 38.2 |
|
17
GPT-5.4 Mini
|
121.4 tok/s | 1.8B | 1–2 | 0.3 | 24.1 |
|
18
Claude Opus 4.8
|
66.0 tok/s | 1.5B 2 | 15–17 | — | 41.8 |
19
GLM 5.3 Flash
|
44.7 tok/s | 1.4B 2 | 1 Unlimited | — | 41.8 |
|
20
Claude Opus 4.7
|
67.6 tok/s | 1.0B 2 | 15–17 | — | 40.7 |
21
Qwen 3.8 Flash
|
57.2 tok/s | 910.0M 2 | 1 Unlimited | — | — |
|
22
GPT-5
|
50.0 tok/s | 897.8M 3 | 3–5 | 1.0 | 23.0 |
|
23
GPT-5.1
|
69.9 tok/s | 760.8M 2 | 3–5 | 0.9 | 24.7 |
|
24
GPT-5.5
|
58.7 tok/s | 667.2M 2 | 14–24 | — | 38.4 |
|
25
Gemini 3.1 Pro
|
89.4 tok/s | 663.2M 3 | 7 | 1.0 | 29.7 |
|
26
GPT-5.2 Codex
|
50.5 tok/s | 654.6M 3 | 5–9 | 0.8 | 41.2 |
|
27
GPT-5.1 Codex Mini
|
101.4 tok/s | 555.0M 6 | 1 | 0.7 | 31.3 |
|
28
GPT-5.3 Codex
|
59.1 tok/s | 497.3M 8 | 5–9 | — | 32.5 |
|
29
Gemini 3 Pro
|
77.3 tok/s | 410.9M 9 | 4 | 1.0 | 40.6 |
|
30
GPT-5.6 Sol
|
45.5 tok/s | 392.0M 9 | 11–18 | 1.0 | 47.0 |
|
31
Qwen 3.7 Flash
|
110.5 tok/s | 375.6M 9 | 1 Unlimited | — | — |
|
32
Gemini 3.8 Flash
|
111.9 tok/s | 302.9M 12 | 1.5–2.5 | — | 40.9 |
33
MiniMax M2.7
|
62.9 tok/s | 288.3M 12 | 1 | — | 22.8 |
|
34
Claude Opus 5
|
69.8 tok/s | 278.4M 12 | 15–22 | — | 50.8 |
|
35
DeepSeek V3.2
|
27.6 tok/s | 261.2M 8 | 1 | — | 25.1 |
|
36
GLM 5.1
|
42.5 tok/s | 249.9M 11 | 2 | — | 26.1 |
|
37
Claude Fable 5 Thinking
|
68.4 tok/s | 231.2M 13 | 36 | — | 49.6 |
38
Space Bunny Alpha
|
55.7 tok/s | 227.3M 13 | 0 | — | — |
|
39
GPT-4.1
|
45.5 tok/s | 201.5M 7 | 6 | — | 12.7 |
|
40
MiniMax M3
|
69.2 tok/s | 199.5M 14 | 1 | — | 29.2 |
|
41
GPT-6 Sol
|
47.1 tok/s | 196.6M 14 | 5.5–9 | — | 47.5 |
|
42
Gemini 2.5 Flash
|
186.2 tok/s | 181.9M | 1 | 0.2 | 9.9 |
|
43
Qwen 3.6 Plus
|
50.2 tok/s | 181.4M 14 | 1 Unlimited | — | 27.0 |
|
44
GLM 5.2
|
61.0 tok/s | 172.2M 14 | 2 | — | 33.7 |
|
45
Qwen 3.7 Max
|
45.9 tok/s | 169.5M 15 | 3 | — | 29.5 |
46
Hy3
|
74.7 tok/s | 154.9M 15 | 1 Unlimited | — | 25.3 |
47
Muse Spark 1.3 Contributor
|
104.7 tok/s | 154.2M 15 | 1 Unlimited | — | — |
48
Kimi K2.5
|
43.0 tok/s | 150.4M 15 | 1 | — | 23.5 |
|
49
Gemini 3.5 Flash
|
143.2 tok/s | 137.1M 16 | 4 | 1.0 | 32.6 |
|
50
Nemotron 3.5 Lightning
|
71.2 tok/s | 133.1M 16 | 0 | — | 12.9 |
|
51
Qwen 3.6 Flash
|
165.0 tok/s | 121.2M 16 | 1 | — | — |
|
52
GLM 5
|
57.6 tok/s | 120.2M 16 | 1 | — | 27.9 |
|
53
Kimi K2.7 Code
|
67.7 tok/s | 118.6M 17 | 1 | — | 25.8 |
|
54
Claude 4 Sonnet
|
62.2 tok/s | 100.6M 36 | 6–7 | — | 29.8 |
|
55
GPT-5.1 Codex Max
|
72.2 tok/s | 98.6M 17 | 4–5 | — | — |
|
56
Claude 4.1 Opus
|
37.1 tok/s | 94.4M 8 | 50–60 | — | 34.5 |
|
57
Gemini 2.5 Pro
|
92.9 tok/s | 89.5M 16 | 4 | — | 25.9 |
|
58
GLM 5 Turbo
|
54.7 tok/s | 86.2M 15 | 1 | — | 26.6 |
|
59
GLM 5V Turbo
|
67.3 tok/s | 84.7M 15 | 1 | — | 23.5 |
|
60
GPT-4.1 mini
|
47.4 tok/s | 80.8M 25 | 1 | — | 10.2 |
61
Grok-4.1 Fast
|
112.7 tok/s | 80.1M 14 | 1 | — | 17.0 |
62
MiMo V2.5 Pro
|
64.3 tok/s | 79.2M 14 | 1 | — | 26.0 |
|
63
Grok-4 Fast
|
156.2 tok/s | 76.7M 14 | 1 | 0.4 | 16.6 |
|
64
Qwen 3.8 Max
|
36.3 tok/s | 74.2M 14 | 2–3 | — | 45.4 |
|
65
Gemini 3.6 Flash
|
160.6 tok/s | 73.7M 14 | 3 | — | 34.0 |
|
66
Kimi K2.6
|
51.8 tok/s | 72.7M 15 | 1 | — | 27.0 |
|
67
Muse Spark 1.2 Contributor
|
131.9 tok/s | 71.9M 15 | 1 Unlimited | — | — |
|
68
Qwen 3.5 Flash
|
95.1 tok/s | 68.0M 15 | 1 | — | — |
|
69
GLM 5.3
|
66.4 tok/s | 67.5M 16 | 2–3 | 0.9 | 44.8 |
|
70
Qwen 3.5 Plus
|
57.6 tok/s | 63.5M 16 | 1 | — | — |
|
71
Gemini 3.7 Flash
|
142.3 tok/s | 62.7M 16 | 2 | — | 39.1 |
|
72
Claude 3.5 Haiku
|
55.2 tok/s | 45.4M 48 | 1 | — | 12.2 |
|
73
Grok Build 0.1
|
125.7 tok/s | 41.5M 20 | 1 | — | — |
|
74
Grok 4.6
|
57.2 tok/s | 41.5M 20 | 2–4 | — | 44.3 |
75
Ling 3.0 Flash
|
239.0 tok/s | 41.1M 21 | 1 Unlimited | — | 20.1 |
|
76
Nemotron 3 Ultra
|
28.4 tok/s | 40.0M 21 | 0 | — | — |
|
77
MiniMax M2.5
|
50.9 tok/s | 39.5M 21 | 1 | — | 22.8 |
|
78
Hy4 Preview
|
53.0 tok/s | 37.4M 21 | 1–2 | — | — |
|
79
MiMo V2.6 Pro
|
40.0 tok/s | 34.4M 21 | 1 Unlimited | — | 46.3 |
|
80
Claude Sonnet 5.5
|
108.3 tok/s | 31.5M 21 | 6–9 | — | 56.0 |
|
81
Kimi K3
|
32.6 tok/s | 30.3M 22 | 7 | — | 43.6 |
|
82
Grok 4.7
|
48.7 tok/s | 29.0M 22 | 1–2 | — | 46.4 |
|
83
Claude Fable 5.1
|
71.3 tok/s | 28.1M 22 | 30–44 | — | 53.4 |
|
84
MiMo V2.6 Flash
|
40.9 tok/s | 26.4M 22 | 0 Unlimited | — | 37.9 |
|
85
Laguna S 2.1
|
65.3 tok/s | 23.6M 23 | 0 | — | — |
|
86
Qwen3 235B A22B
|
41.9 tok/s | 21.0M 21 | 1 | — | — |
|
87
MiMo V2 Pro
|
82.2 tok/s | 18.6M 24 | 1 | — | 41.4 |
|
88
GPT-6 Astra
|
30.9 tok/s | 18.6M 24 | 30–42 | — | 52.7 |
|
89
Claude Opus 5.5
|
57.2 tok/s | 18.3M 24 | 10–18 | — | 57.6 |
|
90
Qwen 3.7 Plus
|
44.6 tok/s | 17.6M 24 | 1 | — | 25.2 |
|
91
Grok 4.5
|
54.3 tok/s | 17.4M 24 | 4 | — | 38.8 |
|
92
Qwen 3.6 Max Preview
|
38.5 tok/s | 16.8M 24 | 4 | — | 28.4 |
|
93
DeepSeek V3.2 Thinking
|
33.0 tok/s | 15.2M 9 | 1 | — | — |
|
94
Ox Alpha
|
29.7 tok/s | 15.1M 25 | 0 | — | — |
|
95
Grok-4.20 Beta
|
163.1 tok/s | 13.6M 26 | 4 | — | — |
|
96
GLM 4.6
|
45.2 tok/s | 13.0M 26 | 1 | — | 14.9 |
|
97
GPT-5 Pro
|
15.1 tok/s | 12.9M 26 | 70 | — | — |
|
98
Grok-4
|
39.6 tok/s | 9.4M 19 | 5 | — | 22.5 |
|
99
Qwen 3.8 27B
|
27.8 tok/s | 8.5M 25 | 0 | — | 33.7 |
|
100
OpenAI o3
|
61.0 tok/s | 8.0M 48 | 4–5 | — | 20.2 |
101
Codestral (2508)
|
109.3 tok/s | 7.4M 27 | 1 | — | — |
|
102
GLM 4.7
|
46.3 tok/s | 7.2M 27 | 1 | — | 34.5 |
|
103
Mistral Medium 3
|
69.0 tok/s | 7.2M 22 | 1 | — | 9.0 |
|
104
GPT-6.1 Sol
|
29.4 tok/s | 6.5M 27 | 5.5–8 | — | 51.8 |
|
105
Mistral Medium 3.5
|
100.6 tok/s | 6.0M 27 | 2 | — | 14.2 |
|
106
GPT-5.2 Codex
|
66.3 tok/s | 5.2M 27 | 8 | — | 41.2 |
|
107
Muse Spark 1.3
|
135.7 tok/s | 5.0M 27 | 1–3 | — | 45.1 |
|
108
Llama 4 Maverick
|
55.6 tok/s | 3.4M 6 | 1 | — | 10.0 |
|
109
Kimi K2 Thinking
|
73.4 tok/s | 3.0M 31 | 1 | — | 22.0 |
|
110
Grok-4.20
|
175.7 tok/s | 2.8M 31 | 4 | — | 38.0 |
|
111
Grok-4.3
|
110.3 tok/s | 1.4M 33 | 3 | — | 24.9 |
|
112
Qwen3 Coder
|
84.5 tok/s | 1.3M 25 | 2 | — | — |
|
113
Muse Spark 1.2
|
145.9 tok/s | 1.1M 32 | 1 | — | 39.6 |
|
114
Mistral Large 3
|
60.4 tok/s | 911.2K 32 | 1 | — | 5.8 |
|
115
Gemini 2.0 Flash
|
137.8 tok/s | 852.5K 72 | 1 | — | 12.2 |
|
116
Kimi K2 (0905)
|
50.2 tok/s | 641.2K 27 | 1 | — | 12.7 |
|
117
Claude 4 Opus
|
25.3 tok/s | 389.5K 28 | 50–60 | — | 31.7 |
|
118
GPT-4o Mini
|
64.8 tok/s | 187.1K 84 | 1 | — | 6.7 |
|
119
GPT-4o
|
12.2 tok/s | 122.3K 82 | 2 | — | 9.4 |
|
120
OpenAI o4-mini
|
51.3 tok/s | 13.8K 72 | 2 | — | 16.7 |
|
121
GPT-3.5 Turbo
|
22.5 tok/s | 10.2K 68 | 1 | — | 5.5 |
|
122
Llama 3.1 405B
|
0.0 tok/s | 7.6K 32 | 2 | — | — |
|
123
Claude 3.7 Sonnet
|
18.1 tok/s | 6.5K 92 | 6 | — | 15.3 |
|
124
Gemma 4 26B
|
8.7 tok/s | 5.1K 23 | 0 | — | 16.7 |
|
125
DeepSeek R1
|
64.1 tok/s | 1.4K 5 | 1 | — | 20.4 |
|
126
DeepSeek V3
|
51.5 tok/s | 1.1K 13 | 1 | — | 8.5 |
|
127
Claude 3.5 Sonnet
|
39.3 tok/s | 319 97 | 2 | — | 9.8 |
|
128
Grok-3 (Beta)
|
21.9 tok/s | 142 8 | 3 | — | — |
|
129
Llama 3.3 70B
|
30.4 tok/s | 107 34 | 1 | — | — |
|
130
GPT-4 Turbo
|
9.2 tok/s | 62 42 | 10 | — | 7.7 |
How to read these statistics
Real usageUsage combines prompt and completion tokens generated by CodingFleet users during the selected period.
Credits and availabilityCredits are charged per request, pro-rata to the tokens used. Models tagged Unlimited cost no credits on the Unlimited plan and above (Unlimited, Elite, Ultimate, Ultimate Max); every other model is charged the credits shown, on every plan. Legacy models are no longer selectable.
IntelligenceA composite score out of 100 covering reasoning, coding and knowledge — the same number the Auto model router weighs against price when it picks a model for you.
