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
Claude Opus 5
|
230.3 chars/s | 147.2M 12 | 15–17 | — | 60.7 |
|
2
Claude Fable 5 Thinking
|
181.0 chars/s | 183.0M 11 | 34 | — | 59.9 |
3
GPT-5.6 Sol
|
385.6 chars/s | 355.8M 8 | 14–24 | 1.0 | 58.9 |
4
Kimi K3
|
88.6 chars/s | 19.6M 20 | 7 | — | 57.1 |
|
5
Claude Opus 4.8
|
140.7 chars/s | 1.2B 1 | 16–18 | — | 55.7 |
|
6
GPT-5.6 Terra
|
577.2 chars/s | 438.3M 6 | 5–9 | 1.0 | 55.0 |
|
7
GPT-5.5
|
205.1 chars/s | 658.7M 2 | 13–22 | — | 54.8 |
8
Muse Spark 1.2
|
325.0 chars/s | 19.5K 24 | 1 | — | 54.1 |
9
Grok 4.5
|
480.8 chars/s | 6.7M 24 | 4 | — | 53.8 |
|
10
Claude Opus 4.7
|
140.2 chars/s | 1.0B 1 | 15–17 | — | 53.5 |
|
11
Claude Sonnet 5
|
248.3 chars/s | 731.1M 1 | 7–8 | — | 53.4 |
12
Qwen 3.8 Max
|
92.7 chars/s | 17.0M 21 | 3 | — | 53.4 |
|
13
GPT-5.4
|
147.0 chars/s | 2.3B | 7–11 | 0.9 | 51.4 |
|
14
GPT-5.6 Luna
|
425.7 chars/s | 896.8M | 1 | 0.0 | 51.2 |
15
GLM 5.2
|
250.0 chars/s | 141.6M 13 | 2 | — | 51.1 |
16
Gemini 3.5 Flash
|
320.2 chars/s | 137.1M 14 | 4 | 1.0 | 50.2 |
|
17
Gemini 3.6 Flash
|
515.0 chars/s | 60.0M 15 | 5 | — | 50.1 |
18
DeepSeek V4 Flash
|
583.6 chars/s | 7.3B | 1 | — | 49.9 |
|
19
Gemini 3.1 Pro
|
182.7 chars/s | 613.6M 2 | 6 | 1.0 | 46.5 |
|
20
Qwen 3.7 Max
|
133.7 chars/s | 169.3M 12 | 3 | — | 46.0 |
21
MiniMax M3
|
283.9 chars/s | 163.7M 12 | 1 | — | 44.4 |
|
22
GPT-5.3 Codex
|
109.9 chars/s | 497.3M 6 | 5–9 | — | 44.3 |
|
23
DeepSeek V4 Pro
|
252.8 chars/s | 6.5B | 1 | 0.7 | 44.3 |
|
24
Kimi K2.6
|
62.6 chars/s | 71.6M 14 | 1 | — | 44.2 |
|
25
GPT-5.2
|
117.4 chars/s | 2.9B | 4–8 | 0.8 | 42.2 |
26
MiMo V2.5 Pro
|
192.7 chars/s | 68.8M 14 | 1 | — | 42.2 |
|
27
Kimi K2.7 Code
|
180.7 chars/s | 91.3M 13 | 1 | — | 41.9 |
28
Hy3
|
148.4 chars/s | 81.8M 13 | 1 | — | 41.2 |
|
29
MiMo V2 Pro
|
302.5 chars/s | 18.6M 21 | 1 | — | 40.3 |
|
30
GLM 5.1
|
134.9 chars/s | 245.4M 8 | 2 | — | 40.2 |
|
31
GPT-5.2 Codex
|
111.8 chars/s | 646.4M 2 | 5–9 | 0.8 | 40.1 |
|
32
GPT-5.2 Codex
|
225.7 chars/s | 5.2M 25 | 8 | — | 40.1 |
|
33
GPT-5.4 Mini
|
354.5 chars/s | 1.6B 1 | 1–2 | 0.1 | 40.0 |
|
34
Qwen 3.6 Max Preview
|
50.5 chars/s | 16.8M 21 | 4 | — | 40.0 |
|
35
Gemini 3 Pro
|
160.0 chars/s | 411.0M 7 | 4 | 1.0 | 39.6 |
|
36
Qwen 3.6 Plus
|
74.0 chars/s | 172.3M 11 | 1 | — | 39.6 |
|
37
GLM 5
|
186.2 chars/s | 120.2M 13 | 1 | — | 39.5 |
|
38
Qwen 3.7 Plus
|
258.4 chars/s | 16.0M 23 | 1 | — | 39.0 |
|
39
MiniMax M2.7
|
195.0 chars/s | 182.6M 11 | 1 | — | 38.1 |
|
40
GLM 5 Turbo
|
164.2 chars/s | 86.2M 13 | 1 | — | 38.1 |
|
41
Claude Opus 4.6
|
129.1 chars/s | 2.6B | 15–17 | 1.0 | 37.8 |
|
42
Grok-4.3
|
349.3 chars/s | 1.4M 28 | 3 | — | 37.6 |
|
43
Grok-4.20
|
700.7 chars/s | 2.8M 29 | 4 | — | 37.0 |
|
44
GPT-5.1
|
167.6 chars/s | 707.0M 1 | 3–5 | 0.9 | 36.9 |
|
45
Claude Sonnet 4.6
|
144.9 chars/s | 3.2B | 9–10 | 1.0 | 35.9 |
|
46
Kimi K2.5
|
95.5 chars/s | 141.1M 13 | 1 | — | 35.4 |
|
47
Claude Opus 4.5
|
177.5 chars/s | 2.0B | 15–17 | — | 34.7 |
|
48
GPT-5
|
92.9 chars/s | 1.6B 1 | 3–5 | 1.0 | 34.7 |
|
49
GLM 5V Turbo
|
234.1 chars/s | 60.2M 15 | 1 | — | 34.5 |
|
50
GLM 4.7
|
92.0 chars/s | 7.3M 24 | 1 | — | 33.7 |
|
51
Claude 4.1 Opus
|
112.6 chars/s | 133.3M 12 | 50–60 | — | 33.7 |
|
52
MiniMax M2.5
|
142.6 chars/s | 39.5M 21 | 1 | — | 33.7 |
|
53
Grok-4
|
120.6 chars/s | 13.4M 18 | 5 | — | 33.3 |
|
54
Kimi K2 Thinking
|
138.5 chars/s | 3.0M 29 | 1 | — | 32.7 |
|
55
Claude 4 Opus
|
82.4 chars/s | 389.5K 18 | 50–60 | — | 31.0 |
|
56
GPT-5.1 Codex Mini
|
263.8 chars/s | 555.0M 5 | 1 | 0.7 | 30.6 |
|
57
OpenAI o3
|
101.5 chars/s | 22.5M 22 | 4–5 | — | 30.4 |
58
Mistral Medium 3.5
|
373.7 chars/s | 5.6M 25 | 2 | — | 29.9 |
|
59
Claude 4 Sonnet
|
159.8 chars/s | 897.6M 4 | 6–7 | 0.7 | 28.9 |
|
60
Gemini 3 Flash
|
304.0 chars/s | 2.1B | 1 | 0.3 | 27.4 |
|
61
Gemini 2.5 Pro
|
159.0 chars/s | 236.1M 3 | 4 | 0.7 | 25.8 |
62
Gemma 4 26B
|
79.6 chars/s | 10.3M 22 | 0 | — | 25.7 |
|
63
OpenAI o4-mini
|
123.3 chars/s | 14.3K 56 | 2 | — | 25.6 |
|
64
GPT-5 Mini
|
139.1 chars/s | 2.2B | 1–2 | 0.7 | 25.3 |
|
65
DeepSeek V3.2
|
102.5 chars/s | 469.0M 4 | 1 | 0.2 | 24.7 |
|
66
Claude 3.7 Sonnet
|
164.5 chars/s | 15.7M 45 | 6–7 | — | 23.5 |
|
67
Kimi K2 (0905)
|
184.7 chars/s | 1.6M 29 | 1 | — | 23.5 |
|
68
GLM 4.6
|
159.0 chars/s | 13.0M 22 | 1 | — | 23.0 |
|
69
DeepSeek R1
|
273.3 chars/s | 1.4K 7 | 1 | — | 20.1 |
|
70
GPT-4.1
|
178.8 chars/s | 246.4M 4 | 6 | — | 19.4 |
|
71
Grok-4.1 Fast
|
165.2 chars/s | 80.1M 13 | 1 | — | 16.9 |
|
72
Grok-4 Fast
|
373.5 chars/s | 76.7M 13 | 1 | 0.4 | 16.5 |
|
73
Mistral Large 3
|
253.3 chars/s | 823.1K 28 | 1 | — | 15.9 |
|
74
GPT-4.1 mini
|
219.2 chars/s | 117.9M 13 | 1 | — | 14.8 |
|
75
Llama 4 Maverick
|
248.4 chars/s | 3.9M 3 | 1 | — | 14.3 |
|
76
DeepSeek V3
|
204.1 chars/s | 1.1K 13 | 1 | — | 14.2 |
|
77
Gemini 2.5 Flash
|
374.9 chars/s | 295.2M 8 | 1 | 0.3 | 14.1 |
|
78
Mistral Medium 3
|
262.2 chars/s | 7.6M 22 | 1 | — | 12.5 |
|
79
Claude 3.5 Haiku
|
202.8 chars/s | 103.9M 29 | 1 | — | 12.3 |
|
80
Gemini 2.0 Flash
|
531.3 chars/s | 21.0M 28 | 1 | — | 12.3 |
|
81
Claude 3.5 Sonnet
|
167.6 chars/s | 319 78 | 2 | — | 9.9 |
|
82
GPT-4o
|
54.3 chars/s | 122.3K 66 | 2 | — | 9.6 |
|
83
GPT-4 Turbo
|
43.7 chars/s | 62 31 | 10 | — | 7.9 |
|
84
GPT-4o Mini
|
16.6 chars/s | 184.9K 67 | 1 | — | 6.9 |
|
85
GPT-3.5 Turbo
|
85.0 chars/s | 10.2K 59 | 1 | — | 3.6 |
|
86
Claude Sonnet 4.5
|
159.1 chars/s | 4.6B | 7–8 | 0.5 | — |
|
87
DeepSeek V3.2 Thinking
|
51.7 chars/s | 27.9M 9 | 1 | — | — |
|
88
Qwen3 235B A22B
|
170.6 chars/s | 22.4M 20 | 1 | — | — |
|
89
Claude Haiku 4.5
|
341.1 chars/s | 5.1B | 1–2 | 0.2 | — |
|
90
Codestral (2508)
|
455.9 chars/s | 7.4M 24 | 1 | — | — |
|
91
GPT-5 Pro
|
35.0 chars/s | 12.9M 22 | 70 | — | — |
|
92
GPT-5.1 Codex Max
|
196.7 chars/s | 98.6M 13 | 4–5 | — | — |
|
93
Ling 3.0 Flash
|
637.4 chars/s | 8.6M 22 | 0 | — | — |
|
94
Llama 3.3 70B
|
136.6 chars/s | 107 25 | 1 | — | — |
|
95
Llama 3.1 405B
|
110.6 chars/s | 240.1K 18 | 2 | — | — |
|
96
Laguna S 2.1
|
303.6 chars/s | 12.0M 22 | 0 | — | — |
|
97
Qwen3 Coder
|
322.3 chars/s | 2.0M 24 | 2 | — | — |
|
98
Qwen 3.5 Flash
|
346.2 chars/s | 68.0M 14 | 1 | — | — |
|
99
Qwen 3.5 Plus
|
178.5 chars/s | 63.5M 15 | 1 | — | — |
|
100
Qwen 3.6 Flash
|
271.8 chars/s | 121.2M 13 | 1 | — | — |
|
101
Qwen 3.7 Flash
|
407.1 chars/s | 122.4M 13 | 1 | — | — |
|
102
Grok-3 (Beta)
|
99.0 chars/s | 142 8 | 3 | — | — |
|
103
Grok-3 Mini (Beta)
|
269.6 chars/s | 1.5M 12 | 1 | — | — |
|
104
Grok-4.20 Beta
|
627.6 chars/s | 13.6M 23 | 4 | — | — |
|
105
Grok Build 0.1
|
334.7 chars/s | 39.3M 21 | 1 | — | — |
|
106
Nemotron 3 Ultra
|
176.9 chars/s | 26.3M 21 | 0 | — | — |
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.