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
—
Characters 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
GLM 5.1
|
134.6 chars/s | 246.6M 9 | 2 | — | 41.0 |
2
Kimi K2.5
|
95.5 chars/s | 141.1M 13 | 1 | — | 36.0 |
3
Gemini 3.6 Flash
|
530.5 chars/s | 68.2M 14 | 3 | — | 51.6 |
|
4
Gemini 3.7 Flash
|
540.2 chars/s | 24.8M 22 | 2 | — | 56.0 |
5
GPT-5.1 Codex Max
|
196.7 chars/s | 98.6M 14 | 4–5 | — | — |
|
6
GPT-5.5
|
204.8 chars/s | 660.4M 2 | 13–22 | — | 56.3 |
|
7
GPT-5.6 Sol
|
397.9 chars/s | 362.1M 7 | 14–24 | 1.0 | 60.9 |
8
Claude 4.1 Opus
|
112.8 chars/s | 123.9M 11 | 50–60 | — | 34.5 |
|
9
Claude Opus 4.5
|
177.5 chars/s | 2.0B | 15–17 | — | 41.9 |
|
10
Claude Opus 4.6
|
129.1 chars/s | 2.6B | 15–17 | 1.0 | 38.8 |
|
11
Claude Opus 4.7
|
140.2 chars/s | 1.0B 1 | 15–17 | — | 55.0 |
|
12
Claude Opus 4.8
|
143.4 chars/s | 1.3B 1 | 16–18 | — | 57.3 |
|
13
Claude Sonnet 4.6
|
145.0 chars/s | 3.2B | 9–10 | 1.0 | 36.8 |
|
14
Claude Sonnet 5
|
330.5 chars/s | 126.7M 14 | 6–12 | — | 53.4 |
15
MiMo V2 Pro
|
302.5 chars/s | 18.6M 23 | 1 | — | 41.4 |
|
16
Gemini 3.1 Pro
|
183.7 chars/s | 621.1M 2 | 6 | 1.0 | 47.7 |
|
17
Gemini 3.5 Flash
|
320.2 chars/s | 137.1M 14 | 4 | 1.0 | 52.0 |
|
18
GLM 5 Turbo
|
164.2 chars/s | 86.2M 13 | 1 | — | 39.1 |
|
19
GLM 5.2
|
249.6 chars/s | 141.8M 13 | 2 | — | 52.6 |
|
20
GLM 5V Turbo
|
234.1 chars/s | 60.3M 15 | 1 | — | 35.3 |
|
21
GPT-5.6 Terra
|
604.7 chars/s | 762.4M 1 | 5–9 | 1.0 | 56.6 |
22
Mistral Medium 3
|
262.8 chars/s | 7.5M 21 | 1 | — | 12.5 |
|
23
Codestral (2508)
|
455.9 chars/s | 7.4M 24 | 1 | — | — |
|
24
Kimi K2.6
|
63.2 chars/s | 71.9M 14 | 1 | — | 45.1 |
25
Qwen 3.7 Flash
|
361.7 chars/s | 169.3M 12 | 1 | — | — |
|
26
Qwen 3.7 Max
|
133.7 chars/s | 169.3M 12 | 3 | — | 46.7 |
27
Hy3
|
151.4 chars/s | 97.8M 14 | 1 | — | 42.2 |
|
28
GPT-5
|
91.6 chars/s | 1.5B 1 | 3–5 | 1.0 | 35.3 |
|
29
Gemini 3 Pro
|
159.9 chars/s | 410.9M 7 | 4 | 1.0 | 40.6 |
|
30
GPT-5.4
|
148.0 chars/s | 2.3B | 8–12 | 0.9 | 53.1 |
|
31
GPT-5.1
|
167.6 chars/s | 707.0M 1 | 3–5 | 0.9 | 37.5 |
|
32
GPT-5.2 Codex
|
111.8 chars/s | 646.4M 2 | 5–9 | 0.8 | 41.2 |
|
33
GPT-5.2
|
117.4 chars/s | 2.9B | 4–8 | 0.8 | 43.3 |
|
34
Gemini 2.5 Pro
|
156.6 chars/s | 180.0M 2 | 4 | 0.7 | 25.9 |
|
35
GPT-5 Mini
|
138.4 chars/s | 2.2B | 1–2 | 0.7 | 31.6 |
|
36
Claude 4 Sonnet
|
159.0 chars/s | 774.3M 5 | 6–7 | 0.7 | 29.8 |
|
37
GPT-5.1 Codex Mini
|
263.8 chars/s | 555.0M 5 | 1 | 0.7 | 31.3 |
38
DeepSeek V4 Pro
|
254.7 chars/s | 7.8B | 1–3 | 0.6 | 53.2 |
|
39
DeepSeek V4 Flash
|
538.3 chars/s | 8.2B | 1 | 0.6 | 51.8 |
|
40
Qwen 3.6 Flash
|
271.8 chars/s | 121.2M 13 | 1 | — | — |
41
Gemma 4 26B
|
81.5 chars/s | 12.6M 22 | 0 | — | 26.1 |
|
42
GPT-5.3 Codex
|
109.9 chars/s | 497.3M 6 | 5–9 | — | 45.5 |
|
43
Kimi K2.7 Code
|
180.6 chars/s | 95.4M 14 | 1 | — | 43.0 |
|
44
Claude Sonnet 4.5
|
159.1 chars/s | 4.6B | 7–8 | 0.5 | — |
45
Grok-4 Fast
|
373.5 chars/s | 76.7M 13 | 1 | 0.4 | 16.6 |
|
46
Claude Fable 5 Thinking
|
181.7 chars/s | 194.0M 12 | 36 | — | 62.1 |
47
MiniMax M2.7
|
196.2 chars/s | 184.4M 12 | 1 | — | 38.9 |
|
48
Gemini 3 Flash
|
304.8 chars/s | 2.1B | 1 | 0.2 | 27.9 |
|
49
GPT-5.4 Mini
|
354.7 chars/s | 1.6B 1 | 1–2 | 0.1 | 40.9 |
|
50
Gemini 2.5 Flash
|
378.4 chars/s | 272.2M 8 | 1 | 0.1 | 14.2 |
|
51
DeepSeek V3.2
|
104.6 chars/s | 448.3M 4 | 1 | 0.1 | 25.1 |
|
52
Claude Haiku 4.5
|
342.3 chars/s | 5.2B | 1–2 | 0.1 | — |
|
53
GPT-5.6 Luna
|
374.4 chars/s | 1.4B 1 | 1 | 0.0 | 52.3 |
|
54
GLM 4.7
|
91.8 chars/s | 7.2M 24 | 1 | — | 34.5 |
|
55
Qwen3 235B A22B
|
170.0 chars/s | 21.9M 19 | 1 | — | — |
|
56
Claude 3.5 Sonnet
|
167.6 chars/s | 319 82 | 2 | — | 9.8 |
|
57
GPT-3.5 Turbo
|
85.0 chars/s | 10.2K 63 | 1 | — | 3.2 |
|
58
GPT-4 Turbo
|
43.7 chars/s | 62 35 | 10 | — | 7.7 |
|
59
GPT-4.1
|
177.4 chars/s | 216.3M 4 | 6 | — | 19.6 |
|
60
GPT-4o
|
54.3 chars/s | 122.3K 70 | 2 | — | 9.4 |
|
61
GPT-4o Mini
|
16.6 chars/s | 184.9K 71 | 1 | — | 6.7 |
|
62
GPT-5 Pro
|
35.0 chars/s | 12.9M 22 | 70 | — | — |
|
63
Claude 3.7 Sonnet
|
160.5 chars/s | 14.2M 47 | 6–7 | — | 27.6 |
|
64
Claude 4 Opus
|
82.4 chars/s | 389.5K 22 | 50–60 | — | 31.7 |
|
65
Claude Opus 5
|
199.8 chars/s | 8.5M 22 | 15–22 | — | 62.5 |
|
66
DeepSeek R1
|
273.3 chars/s | 1.4K 6 | 1 | — | 20.4 |
|
67
DeepSeek V3
|
204.1 chars/s | 1.1K 13 | 1 | — | 14.2 |
|
68
Gemini 2.0 Flash
|
531.5 chars/s | 17.0M 34 | 1 | — | 12.2 |
|
69
Grok-3 Mini (Beta)
|
263.1 chars/s | 1.5M 12 | 1 | — | — |
|
70
Grok-4.3
|
349.3 chars/s | 1.4M 28 | 3 | — | 37.9 |
|
71
Grok 4.5
|
399.8 chars/s | 8.2M 23 | 4 | — | 55.8 |
|
72
Grok 4.6
|
389.1 chars/s | 4.6M 25 | 3 | — | 60.9 |
|
73
Grok Build 0.1
|
328.3 chars/s | 39.8M 21 | 1 | — | — |
|
74
MiMo V2.5 Pro
|
201.2 chars/s | 74.4M 13 | 1 | — | 42.9 |
|
75
GLM 4.6
|
159.0 chars/s | 13.0M 22 | 1 | — | 23.4 |
|
76
GLM 5.3
|
47.1 chars/s | 407 20 | 3 | — | — |
|
77
Ling 3.0 Flash
|
637.4 chars/s | 8.6M 22 | 0 | — | 37.8 |
78
Llama 3.3 70B
|
136.6 chars/s | 107 29 | 1 | — | — |
|
79
Llama 4 Maverick
|
247.9 chars/s | 3.9M 6 | 1 | — | 14.5 |
|
80
Llama 3.1 405B
|
109.6 chars/s | 238.6K 22 | 2 | — | — |
|
81
Muse Spark 1.2
|
789.3 chars/s | 967.3K 28 | 1 | — | 56.8 |
|
82
MiniMax M2.5
|
142.6 chars/s | 39.5M 21 | 1 | — | 34.5 |
|
83
Mistral Large 3
|
253.3 chars/s | 823.1K 28 | 1 | — | 4.1 |
|
84
Mistral Medium 3.5
|
373.7 chars/s | 5.6M 25 | 2 | — | 30.4 |
|
85
Kimi K2 (0905)
|
184.7 chars/s | 1.6M 29 | 1 | — | 19.7 |
|
86
Kimi K2 Thinking
|
138.5 chars/s | 3.0M 29 | 1 | — | 33.5 |
|
87
Kimi K3
|
99.6 chars/s | 22.9M 22 | 7 | — | 59.7 |
|
88
Nemotron 3 Ultra
|
178.2 chars/s | 28.6M 22 | 0 | — | — |
|
89
Nemotron 3.5 Lightning
|
462.7 chars/s | 109.1M 15 | 0 | — | 23.6 |
|
90
OpenAI o3
|
98.3 chars/s | 17.3M 29 | 4–5 | — | 31.1 |
|
91
OpenAI o4-mini
|
142.4 chars/s | 13.8K 60 | 2 | — | 26.1 |
|
92
GPT-5.2 Codex
|
225.7 chars/s | 5.2M 25 | 8 | — | 41.2 |
|
93
Laguna S 2.1
|
235.8 chars/s | 22.9M 22 | 0 | — | — |
|
94
Qwen 3.5 Flash
|
346.2 chars/s | 68.0M 14 | 1 | — | — |
|
95
Qwen 3.5 Plus
|
178.5 chars/s | 63.5M 15 | 1 | — | — |
|
96
Qwen 3.6 Max Preview
|
50.5 chars/s | 16.8M 21 | 4 | — | 41.1 |
|
97
Qwen 3.6 Plus
|
75.3 chars/s | 175.2M 11 | 1 | — | 40.5 |
|
98
Qwen 3.7 Plus
|
251.7 chars/s | 16.1M 23 | 1 | — | 39.4 |
|
99
Grok-3 (Beta)
|
99.0 chars/s | 142 7 | 3 | — | — |
|
100
GPT-4.1 mini
|
216.8 chars/s | 101.7M 14 | 1 | — | 14.8 |
|
101
GLM 5
|
186.2 chars/s | 120.2M 13 | 1 | — | 40.6 |
|
102
Claude 3.5 Haiku
|
201.6 chars/s | 89.4M 32 | 1 | — | 12.2 |
|
103
DeepSeek V3.2 Thinking
|
62.3 chars/s | 24.6M 8 | 1 | — | — |
|
104
Grok-4
|
118.9 chars/s | 13.2M 18 | 5 | — | 34.1 |
|
105
Grok-4.1 Fast
|
165.2 chars/s | 80.1M 13 | 1 | — | 17.0 |
|
106
Grok-4.20
|
700.7 chars/s | 2.8M 29 | 4 | — | 38.0 |
|
107
Grok-4.20 Beta
|
627.6 chars/s | 13.6M 23 | 4 | — | — |
|
108
MiniMax M3
|
284.2 chars/s | 165.8M 12 | 1 | — | 45.4 |
|
109
Qwen3 Coder
|
325.9 chars/s | 2.0M 24 | 2 | — | — |
|
110
Qwen 3.8 Max
|
87.9 chars/s | 17.7M 23 | 3 | — | 58.1 |
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. One-credit models are unlimited on eligible Unlimited and Elite plans; 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.