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
GPT-6 Luna
|
91.8 tok/s | 24.1B | 0.2–0.6 Unlimited | 0.5 | 38.1 |
2
DeepSeek V4.1 Flash
|
163.7 tok/s | 17.3B | 1 Unlimited | 1.0 | 39.5 |
|
3
DeepSeek V4 Pro
|
82.2 tok/s | 14.5B | 2–3.5 | 0.7 | 36.0 |
|
4
DeepSeek V4 Flash
|
155.0 tok/s | 13.5B | 1 | 0.8 | 34.3 |
|
5
GPT-5.6 Luna
|
82.0 tok/s | 9.5B | 0.5–0.9 Unlimited | 0.5 | 37.3 |
6
Claude Haiku 4.5
|
115.5 tok/s | 5.1B | 2–3 | 0.1 | — |
7
GLM 5.3 Flash
|
40.8 tok/s | 4.7B | 1 Unlimited | — | 41.8 |
|
8
Claude Sonnet 4.5
|
54.9 tok/s | 4.0B | 7–8 | 0.5 | — |
|
9
Claude Sonnet 4.6
|
57.1 tok/s | 3.2B | 9–10 | 1.0 | 30.1 |
|
10
GPT-5.2
|
47.7 tok/s | 2.9B | 4–8 | 0.8 | 30.4 |
|
11
Claude Opus 4.6
|
48.4 tok/s | 2.6B | 15–17 | 1.0 | 31.9 |
|
12
GPT-5.6 Terra
|
69.9 tok/s | 2.5B | 5–7.5 | 0.8 | 42.1 |
|
13
GPT-5.4
|
65.2 tok/s | 2.3B 1 | 8–12 | 0.9 | 39.0 |
14
Gemini 3 Flash
|
141.3 tok/s | 2.1B 1 | 2 | 0.2 | 17.9 |
|
15
Claude Sonnet 5
|
91.0 tok/s | 2.0B 1 | 6.8–10 | — | 38.2 |
|
16
Claude Opus 4.5
|
57.0 tok/s | 2.0B 1 | 15–17 | — | 29.1 |
|
17
GPT-5 Mini
|
63.7 tok/s | 2.0B 4 | 1–2 | 0.4 | 25.8 |
|
18
GPT-5.4 Mini
|
121.4 tok/s | 1.8B | 1–2 | 0.3 | 24.1 |
19
Qwen 3.8 Flash
|
62.6 tok/s | 1.6B 1 | 1 Unlimited | — | — |
|
20
Claude Opus 4.8
|
65.7 tok/s | 1.6B 2 | 15–17 | — | 41.8 |
|
21
Claude Opus 4.7
|
67.1 tok/s | 1.1B 2 | 15–17 | — | 40.7 |
22
Space Bunny Alpha
|
58.7 tok/s | 780.5M 2 | 0 | — | — |
|
23
GPT-5.1
|
69.9 tok/s | 760.8M 3 | 3–5 | 0.9 | 24.7 |
|
24
Gemini 3.1 Pro
|
89.0 tok/s | 673.8M 3 | 7 | 1.0 | 29.7 |
|
25
GPT-5.5
|
58.7 tok/s | 667.2M 3 | 16–26 | — | 38.4 |
|
26
GPT-5.2 Codex
|
50.5 tok/s | 654.6M 4 | 5–9 | 0.8 | 41.2 |
|
27
GPT-6.1 Sol
|
35.3 tok/s | 577.3M 5 | 5.5–8 | 1.0 | 51.8 |
|
28
GPT-5.1 Codex Mini
|
101.4 tok/s | 555.0M 7 | 1 | 0.7 | 31.3 |
|
29
Claude Haiku 5.5
|
179.4 tok/s | 510.9M 9 | 0.5–1 Unlimited | — | 43.4 |
|
30
GPT-5.3 Codex
|
59.1 tok/s | 497.3M 9 | 5–9 | — | 32.5 |
|
31
Gemini 3.8 Flash
|
104.9 tok/s | 486.4M 9 | 1.5–2.5 | — | 40.9 |
|
32
Claude Sonnet 5.5
|
116.0 tok/s | 477.8M 10 | 5–8 | — | 56.0 |
|
33
GPT-5
|
50.3 tok/s | 461.7M 12 | 3–5 | 1.0 | 23.0 |
|
34
Qwen 3.7 Flash
|
109.6 tok/s | 445.1M 9 | 1 Unlimited | — | — |
35
Ling 3.1 Flash
|
73.4 tok/s | 436.5M 9 | 0.5 Unlimited | — | 41.1 |
|
36
Gemini 3 Pro
|
77.3 tok/s | 410.9M 9 | 4 | 1.0 | 40.6 |
|
37
GPT-5.6 Sol
|
45.5 tok/s | 392.0M 9 | 11–18 | 1.0 | 47.0 |
38
Muse Spark 1.3 Contributor
|
105.7 tok/s | 338.3M 11 | 1 Unlimited | — | — |
39
MiMo V2.6 Pro
|
43.1 tok/s | 323.5M 12 | 1 | 0.0 | 46.3 |
|
40
GPT-6 Sol
|
54.6 tok/s | 315.7M 12 | 5.5–9 | 1.0 | 47.6 |
|
41
Claude Opus 5
|
69.3 tok/s | 303.0M 12 | 15–22 | — | 50.8 |
42
MiniMax M2.7
|
62.9 tok/s | 290.7M 12 | 2 | — | 22.8 |
|
43
GLM 5.3
|
63.1 tok/s | 289.2M 12 | 2–3 | 0.9 | 44.8 |
|
44
GLM 5.1
|
42.5 tok/s | 249.9M 12 | 2 | — | 26.1 |
|
45
Claude Fable 5 Thinking
|
68.5 tok/s | 231.2M 14 | 36 | — | 49.6 |
|
46
Claude Opus 5.5
|
68.4 tok/s | 223.5M 16 | 10–18 | — | 57.6 |
|
47
Nemotron 3.5 Lightning
|
56.7 tok/s | 214.2M 16 | 0 | — | 12.9 |
|
48
MiniMax M3
|
69.3 tok/s | 201.1M 16 | 1 | — | 29.2 |
|
49
Qwen 3.6 Plus
|
50.2 tok/s | 182.1M 17 | 1 | — | 27.0 |
|
50
GPT-4.1
|
45.1 tok/s | 176.8M 16 | 6 | — | 12.7 |
|
51
GLM 5.2
|
61.8 tok/s | 173.8M 16 | 4 | — | 33.7 |
|
52
Qwen 3.7 Max
|
45.9 tok/s | 169.5M 17 | 3 | — | 29.5 |
53
Hy3
|
78.1 tok/s | 167.1M 17 | 1 Unlimited | — | 25.3 |
|
54
DeepSeek V3.2
|
29.7 tok/s | 166.0M 25 | 1 | — | 25.1 |
55
Kimi K2.5
|
43.0 tok/s | 150.4M 16 | 1 | — | 23.5 |
|
56
Muse Spark 1.2 Contributor
|
126.7 tok/s | 143.7M 16 | 1 Unlimited | — | — |
|
57
Hy4 Preview
|
69.1 tok/s | 140.3M 16 | 2–3 | — | — |
|
58
MiniMax M3.1 Flash
|
80.0 tok/s | 138.3M 17 | 0.7–1.5 Unlimited | — | 42.7 |
|
59
Nemotron 3.5 Super VL
|
56.8 tok/s | 137.6M 17 | 0 | — | 26.5 |
|
60
Gemini 3.5 Flash
|
143.2 tok/s | 137.1M 17 | 4 | 1.0 | 32.6 |
|
61
Nemotron 3 Ultra
|
29.8 tok/s | 134.5M 17 | 0 | — | — |
|
62
Gemini 2.5 Flash
|
179.3 tok/s | 125.3M 14 | 1 | — | 9.9 |
|
63
Kimi K2.7 Code
|
68.4 tok/s | 122.4M 16 | 1 | — | 25.8 |
|
64
Qwen 3.6 Flash
|
165.0 tok/s | 121.2M 16 | 1 | — | — |
|
65
GLM 5
|
57.6 tok/s | 120.2M 16 | 1 | — | 27.9 |
|
66
MiMo V2.6 Flash
|
49.2 tok/s | 116.6M 17 | 0.5 Unlimited | — | 37.9 |
|
67
Qwen 3.8 Max
|
36.4 tok/s | 104.4M 18 | 2.5–4.5 | — | 45.4 |
|
68
GPT-5.1 Codex Max
|
72.2 tok/s | 98.6M 18 | 4–5 | — | — |
|
69
Claude Fable 5.1
|
75.7 tok/s | 91.1M 18 | 30–44 | — | 53.4 |
|
70
GLM 5 Turbo
|
54.7 tok/s | 86.2M 18 | 1 | — | 26.6 |
|
71
GLM 5V Turbo
|
67.3 tok/s | 84.7M 18 | 1 | — | 23.5 |
|
72
Claude 4.1 Opus
|
33.8 tok/s | 83.6M 2 | 50–60 | — | 34.5 |
73
Grok 4.7
|
57.0 tok/s | 81.8M 17 | 2.5–4 | — | 46.4 |
|
74
MiMo V2.5 Pro
|
64.2 tok/s | 80.3M 17 | 1.5 | — | 26.0 |
|
75
Grok-4.1 Fast
|
112.7 tok/s | 80.1M 17 | 1 | — | 17.0 |
|
76
Gemini 3.6 Flash
|
160.6 tok/s | 73.7M 18 | 3 | — | 34.0 |
|
77
Kimi K2.6
|
51.8 tok/s | 72.7M 19 | 1 | — | 27.0 |
|
78
Grok-4 Fast
|
156.4 tok/s | 72.3M 15 | 1 | 0.4 | 16.6 |
|
79
GPT-4.1 mini
|
46.1 tok/s | 70.4M 42 | 1 | — | 10.2 |
|
80
Gemini 3.7 Flash
|
144.4 tok/s | 68.7M 17 | 4 | — | 39.1 |
|
81
Qwen 3.5 Flash
|
95.1 tok/s | 68.0M 17 | 1 | — | — |
|
82
Qwen 3.5 Plus
|
57.6 tok/s | 63.5M 18 | 1 | — | — |
|
83
Gemini 2.5 Pro
|
92.0 tok/s | 56.8M 36 | 4 | — | 25.9 |
|
84
Laguna S 2.1
|
58.6 tok/s | 47.7M 19 | 0 | — | — |
|
85
Grok 4.6
|
56.7 tok/s | 45.4M 19 | 3.5–5 | — | 44.3 |
|
86
Claude 3.5 Haiku
|
54.6 tok/s | 43.5M 61 | 1 | — | 12.2 |
|
87
Ling 3.0 Flash
|
237.7 tok/s | 41.9M 21 | 1 | — | 20.1 |
|
88
Grok Build 0.1
|
125.7 tok/s | 41.5M 21 | 1 | — | — |
|
89
MiniMax M2.5
|
50.9 tok/s | 39.5M 22 | 1 | — | 22.8 |
|
90
Claude 4 Sonnet
|
59.1 tok/s | 38.0M 71 | 6–7 | — | 29.8 |
91
Mistral Large 4
|
71.3 tok/s | 37.7M 21 | 2 | — | 38.4 |
|
92
Qwen 3.8 27B
|
43.4 tok/s | 33.3M 21 | 0 | — | 33.7 |
|
93
Kimi K3
|
32.6 tok/s | 30.3M 22 | 8 | — | 43.6 |
|
94
Qwen 3.7 Plus
|
44.5 tok/s | 27.2M 22 | 1 | — | 25.2 |
|
95
GPT-6 Astra
|
31.6 tok/s | 23.3M 23 | 30–42 | — | 52.7 |
|
96
Gemini 4 Argon
|
57.5 tok/s | 21.9M 23 | 4–6 | — | 52.6 |
|
97
Qwen3 235B A22B
|
39.3 tok/s | 19.8M 20 | 1 | — | — |
|
98
MiMo V2 Pro
|
82.2 tok/s | 18.6M 24 | 1 | — | 41.4 |
|
99
Muse Spark 1.3
|
112.8 tok/s | 18.2M 24 | 1–3 | — | 45.1 |
|
100
Grok 4.5
|
54.3 tok/s | 17.4M 24 | 4 | — | 38.8 |
|
101
Qwen 3.6 Max Preview
|
38.5 tok/s | 16.8M 24 | 4 | — | 28.4 |
|
102
Ox Alpha
|
29.7 tok/s | 15.1M 26 | 0 | — | — |
|
103
Grok-4.20 Beta
|
163.1 tok/s | 13.6M 27 | 4 | — | — |
|
104
GPT-5 Pro
|
14.8 tok/s | 12.8M 28 | 70 | — | — |
|
105
DeepSeek V3.2 Thinking
|
34.1 tok/s | 10.6M 6 | 1 | — | — |
|
106
Mistral Medium 3.5
|
99.1 tok/s | 9.9M 27 | 2 | — | 14.2 |
|
107
Kimi K3.1 Pro
|
34.8 tok/s | 9.0M 27 | 6.5–8 | — | 55.1 |
|
108
OpenAI o3
|
70.5 tok/s | 7.8M 48 | 4–5 | — | 20.2 |
|
109
Codestral (2508)
|
109.3 tok/s | 7.4M 29 | 1 | — | — |
|
110
GLM 4.7
|
46.3 tok/s | 7.2M 29 | 1 | — | 34.5 |
|
111
GLM 4.6
|
46.4 tok/s | 7.2M 20 | 1 | — | 14.9 |
|
112
Mistral Medium 3
|
68.8 tok/s | 7.1M 23 | 1 | — | 9.0 |
|
113
Grok-4
|
38.1 tok/s | 6.7M 13 | 5 | — | 22.5 |
|
114
GPT-5.2 Codex
|
66.3 tok/s | 5.2M 27 | 8 | — | 41.2 |
|
115
Muse Wonder
|
5.9 tok/s | 3.4M 29 | 17 | — | 52.4 |
|
116
Llama 4 Maverick
|
55.6 tok/s | 3.4M 2 | 1 | — | 9.3 |
|
117
Kimi K2 Thinking
|
73.4 tok/s | 3.0M 31 | 1 | — | 22.0 |
|
118
Grok-4.20
|
175.7 tok/s | 2.8M 31 | 4 | — | 38.0 |
|
119
Grok-4.3
|
110.3 tok/s | 1.4M 33 | 3 | — | 24.9 |
|
120
Muse Spark 1.2
|
145.9 tok/s | 1.1M 33 | 1 | — | 39.6 |
|
121
Mistral Large 3
|
60.4 tok/s | 911.2K 33 | 1 | — | 5.8 |
|
122
Qwen3 Coder
|
83.5 tok/s | 761.8K 23 | 2 | — | — |
|
123
Claude 4 Opus
|
25.3 tok/s | 389.5K 21 | 50–60 | — | 31.7 |
|
124
GPT-4o Mini
|
80.2 tok/s | 187.0K 88 | 1 | — | 6.7 |
|
125
GPT-6.1 Terra
|
65.6 tok/s | 166.0K 30 | 1–2.5 | — | — |
|
126
Kimi K2 (0905)
|
55.3 tok/s | 137.0K 25 | 1 | — | 12.7 |
|
127
GPT-4o
|
6.9 tok/s | 122.2K 86 | 2 | — | 9.4 |
|
128
Gemma 4 26B
|
8.6 tok/s | 21.3K 28 | 0 | — | 16.7 |
|
129
OpenAI o4-mini
|
110.6 tok/s | 13.2K 72 | 2 | — | 16.7 |
|
130
GPT-3.5 Turbo
|
0.0 tok/s | 10.1K 69 | 1 | — | 5.5 |
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.