Models tracked
—
Across the selected period
Community telemetry
See how models perform in the real world.
Usage, speed, value, and coding benchmarks—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 | Coding | LiveBench | WebDev Arena |
|---|---|---|---|---|---|---|---|
1
DeepSeek V4 Flash
|
533.2 chars/s | 5.9B | 1 | — | — | — | — |
|
2
DeepSeek V4 Pro
|
233.8 chars/s | 5.4B | 1 | 0.7 | — | — | — |
3
Claude Haiku 4.5
|
337.8 chars/s | 5.1B | 1 | 0.2 | 72.8 | 71.4 | — |
|
4
Claude Sonnet 4.5
|
159.1 chars/s | 4.6B | 7–8 | 0.5 | 80.4 | 78.3 | 1397.0 |
|
5
Claude Sonnet 4.6
|
145.0 chars/s | 3.2B | 9–10 | 1.0 | 80.0 | 75.3 | — |
6
GPT-5.2
|
117.4 chars/s | 2.9B | 4–8 | 0.8 | 76.1 | 73.6 | 1485.0 |
|
7
Claude Opus 4.6
|
129.1 chars/s | 2.6B | 15–17 | 1.0 | 78.2 | 76.3 | 1547.0 |
|
8
GPT-5.4
|
146.1 chars/s | 2.3B | 6–11 | 0.9 | 77.5 | 80.3 | 1481.0 |
|
9
GPT-5 Mini
|
139.2 chars/s | 2.2B | 1–2 | 0.7 | 66.4 | 72.2 | — |
10
Gemini 3 Flash
|
302.4 chars/s | 2.0B | 1 | 0.3 | 73.9 | 73.6 | 1465.0 |
|
11
Claude Opus 4.5
|
177.5 chars/s | 2.0B | 15–17 | — | 79.7 | 79.8 | 1518.0 |
|
12
GPT-5.4 Mini
|
351.2 chars/s | 1.6B 1 | 1–2 | 0.1 | — | — | — |
|
13
GPT-5
|
93.0 chars/s | 1.6B 1 | 3–5 | 1.0 | 75.3 | 78.6 | 1480.5 |
|
14
Claude Opus 4.8
|
143.1 chars/s | 1.2B 1 | 15–17 | — | — | — | — |
|
15
Claude 4 Sonnet
|
160.6 chars/s | 1.1B 3 | 6–7 | 0.7 | 77.5 | 72.1 | 1381.8 |
|
16
Claude Opus 4.7
|
139.8 chars/s | 1.0B | 15–17 | — | 82.1 | 76.9 | 1503.0 |
|
17
GPT-5.1
|
167.6 chars/s | 707.0M 1 | 3–5 | 0.9 | 72.5 | 72.5 | 1395.0 |
|
18
GPT-5.2 Codex
|
111.8 chars/s | 646.4M 2 | 5–9 | 0.8 | 83.6 | 74.3 | — |
|
19
GPT-5.5
|
201.0 chars/s | 645.1M 2 | 13–22 | — | 82.5 | 80.7 | — |
|
20
Gemini 3.1 Pro
|
180.6 chars/s | 599.5M 3 | 4 | 1.0 | 76.5 | 79.9 | 1500.0 |
|
21
GPT-5.1 Codex Mini
|
263.9 chars/s | 555.0M 5 | 1 | 0.7 | 71.8 | 69.8 | 1248.0 |
|
22
Claude Sonnet 5
|
243.8 chars/s | 519.2M 5 | 6–7 | — | — | — | — |
|
23
GPT-5.3 Codex
|
109.9 chars/s | 497.3M 6 | 5–9 | — | — | — | — |
|
24
DeepSeek V3.2
|
100.6 chars/s | 483.0M 5 | 1 | 0.3 | 68.5 | 62.6 | — |
|
25
Gemini 3 Pro
|
160.0 chars/s | 411.0M 7 | 4 | 1.0 | 74.6 | 79.7 | 1481.0 |
|
26
GPT-5.6 Sol
|
342.4 chars/s | 344.7M 8 | 14–24 | 1.0 | — | — | — |
|
27
Gemini 2.5 Flash
|
369.8 chars/s | 317.6M 8 | 1 | 0.3 | 60.3 | 69.9 | 1304.9 |
|
28
GPT-5.6 Luna
|
647.8 chars/s | 310.3M 9 | 1 | 0.4 | — | — | — |
|
29
GPT-4.1
|
185.9 chars/s | 260.3M 5 | 6 | — | 73.2 | 63.0 | 1256.5 |
|
30
Gemini 2.5 Pro
|
162.9 chars/s | 257.9M 3 | 4 | 0.7 | 72.9 | 79.0 | 1409.1 |
31
GLM 5.1
|
135.2 chars/s | 244.0M 7 | 1 | — | — | — | — |
|
32
GPT-5.6 Terra
|
474.9 chars/s | 212.9M 10 | 6–11 | 1.0 | — | — | — |
33
MiniMax M2.7
|
193.0 chars/s | 174.4M 11 | 1 | — | — | — | — |
34
Qwen 3.6 Plus
|
74.1 chars/s | 172.0M 11 | 1 | — | — | — | — |
|
35
Claude Fable 5 Thinking
|
175.0 chars/s | 171.5M 11 | 34 | — | — | — | — |
|
36
Qwen 3.7 Max
|
133.7 chars/s | 169.3M 12 | 3 | — | — | — | — |
|
37
MiniMax M3
|
283.2 chars/s | 163.7M 12 | 1 | — | — | — | — |
|
38
GPT-4.1 mini
|
214.3 chars/s | 160.7M 7 | 1 | 0.2 | 72.1 | 59.1 | 1194.4 |
|
39
Claude 3.5 Haiku
|
202.3 chars/s | 142.5M 22 | 1 | — | 53.2 | 45.0 | 1133.8 |
40
Kimi K2.5
|
95.0 chars/s | 140.6M 11 | 1 | — | 77.9 | 69.1 | — |
|
41
Claude 4.1 Opus
|
113.8 chars/s | 138.5M 11 | 50–60 | — | 74.0 | 73.5 | 1476.5 |
|
42
Gemini 3.5 Flash
|
320.2 chars/s | 137.1M 11 | 4 | 1.0 | — | — | — |
|
43
GLM 5.2
|
251.8 chars/s | 131.1M 11 | 2 | — | — | — | — |
|
44
GLM 5
|
186.2 chars/s | 120.2M 11 | 1 | — | 73.6 | 68.9 | 1456.0 |
|
45
Qwen 3.6 Flash
|
268.8 chars/s | 111.4M 12 | 1 | — | — | — | — |
|
46
GPT-5.1 Codex Max
|
196.7 chars/s | 98.6M 13 | 4–5 | — | 81.4 | 75.2 | — |
|
47
Qwen 3.7 Flash
|
682.4 chars/s | 94.5M 13 | 1 | — | — | — | — |
|
48
GLM 5 Turbo
|
164.2 chars/s | 86.2M 13 | 1 | — | — | — | — |
49
Grok-4.1 Fast
|
165.2 chars/s | 80.1M 13 | 1 | — | — | — | — |
|
50
Kimi K2.7 Code
|
177.2 chars/s | 78.0M 13 | 1 | — | — | — | — |
|
51
Grok-4 Fast
|
373.5 chars/s | 76.7M 13 | 1 | 0.4 | — | — | — |
|
52
Kimi K2.6
|
62.5 chars/s | 71.5M 14 | 1 | — | — | — | — |
|
53
Qwen 3.5 Flash
|
346.2 chars/s | 68.0M 14 | 1 | — | — | — | — |
54
Hy3
|
155.6 chars/s | 64.5M 15 | 1 | — | — | — | — |
|
55
Qwen 3.5 Plus
|
178.5 chars/s | 63.5M 15 | 1 | — | — | — | — |
56
MiMo V2.5 Pro
|
191.7 chars/s | 58.0M 15 | 1 | — | — | — | — |
|
57
GLM 5V Turbo
|
224.1 chars/s | 55.6M 16 | 1 | — | — | — | — |
|
58
OpenAI o3
|
131.8 chars/s | 45.4M 17 | 4–5 | — | 77.9 | 74.6 | 1188.3 |
|
59
MiniMax M2.5
|
142.6 chars/s | 39.5M 20 | 1 | — | 70.7 | 60.1 | — |
|
60
Grok Build 0.1
|
323.3 chars/s | 39.1M 20 | 1 | — | — | — | — |
|
61
Gemini 3.6 Flash
|
553.0 chars/s | 37.7M 20 | 4 | — | — | — | — |
|
62
Claude Opus 5
|
245.6 chars/s | 30.6M 20 | 15–17 | — | — | — | — |
|
63
DeepSeek V3.2 Thinking
|
50.8 chars/s | 29.3M 5 | 1 | — | 64.6 | 66.6 | — |
|
64
Qwen3 235B A22B
|
160.6 chars/s | 23.4M 20 | 1 | — | 66.4 | 64.9 | — |
|
65
Gemini 2.0 Flash
|
531.6 chars/s | 21.7M 29 | 1 | — | 64.7 | 60.1 | 1035.2 |
|
66
MiMo V2 Pro
|
302.5 chars/s | 18.6M 21 | 1 | — | — | — | — |
|
67
Claude 3.7 Sonnet
|
166.0 chars/s | 17.3M 42 | 6–7 | — | 74.3 | 67.4 | 1356.7 |
|
68
Qwen 3.6 Max Preview
|
50.5 chars/s | 16.8M 20 | 4 | — | — | — | — |
|
69
Kimi K3
|
79.8 chars/s | 16.1M 22 | 7 | — | — | — | — |
|
70
Qwen 3.7 Plus
|
269.5 chars/s | 16.0M 22 | 1 | — | — | — | — |
|
71
Grok-4
|
126.3 chars/s | 14.8M 18 | 5 | — | 71.3 | 72.1 | — |
|
72
Grok-4.20 Beta
|
627.6 chars/s | 13.6M 22 | 4 | — | — | — | — |
|
73
GLM 4.6
|
159.0 chars/s | 13.0M 22 | 1 | — | — | — | — |
|
74
GPT-5 Pro
|
35.0 chars/s | 12.9M 22 | 70 | — | 72.1 | 78.7 | — |
75
Mistral Medium 3
|
263.0 chars/s | 7.7M 22 | 1 | — | 61.5 | 56.6 | 1160.1 |
|
76
GLM 4.7
|
91.9 chars/s | 7.3M 24 | 1 | — | 73.1 | 58.1 | — |
77
Nemotron 3 Ultra
|
183.5 chars/s | 7.1M 24 | 0 | — | — | — | — |
|
78
Gemma 4 26B
|
70.6 chars/s | 6.4M 25 | 0 | — | — | — | — |
|
79
Ling 3.0 Flash
|
510.2 chars/s | 6.3M 25 | 0 | — | — | — | — |
|
80
Codestral (2508)
|
448.3 chars/s | 6.1M 25 | 1 | — | — | — | — |
|
81
Mistral Medium 3.5
|
374.6 chars/s | 5.6M 25 | 2 | — | — | — | — |
|
82
GPT-5.2 Codex
|
225.7 chars/s | 5.2M 25 | 8 | — | — | — | — |
83
Llama 4 Maverick
|
282.8 chars/s | 4.7M | 1 | — | 54.2 | 55.2 | 998.5 |
|
84
OpenAI o4-mini
|
178.9 chars/s | 3.4M 41 | 2 | — | — | — | 1095.1 |
|
85
Grok 4.5
|
324.0 chars/s | 3.1M 27 | 4 | — | — | — | — |
|
86
Laguna S 2.1
|
197.2 chars/s | 3.1M 28 | 0 | — | — | — | — |
|
87
Kimi K2 Thinking
|
138.5 chars/s | 3.0M 28 | 1 | — | — | — | — |
|
88
Grok-4.20
|
700.7 chars/s | 2.8M 28 | 4 | — | — | — | — |
|
89
Qwen3 Coder
|
305.5 chars/s | 2.6M 21 | 2 | — | 73.2 | 60.5 | — |
|
90
Claude 4 Opus
|
131.6 chars/s | 2.2M 16 | 50–60 | — | 73.3 | 72.9 | 1405.5 |
|
91
Kimi K2 (0905)
|
184.7 chars/s | 1.6M 27 | 1 | — | 71.8 | 62.7 | — |
|
92
Grok-3 Mini (Beta)
|
272.1 chars/s | 1.6M 6 | 1 | — | 54.5 | 70.3 | — |
|
93
Grok-4.3
|
349.3 chars/s | 1.4M 26 | 3 | — | — | — | — |
|
94
Mistral Large 3
|
253.3 chars/s | 823.1K 26 | 1 | — | 62.9 | 50.3 | — |
|
95
Llama 3.1 405B
|
100.2 chars/s | 247.5K 20 | 2 | — | 42.7 | 52.4 | 813.7 |
|
96
GPT-4o Mini
|
16.6 chars/s | 184.9K 68 | 1 | — | 43.2 | 41.3 | — |
|
97
GPT-4o
|
254.5 chars/s | 178.0K 67 | 2 | — | — | — | — |
|
98
GPT-3.5 Turbo
|
85.0 chars/s | 10.2K 58 | 1 | — | — | — | — |
|
99
Llama 3.3 70B
|
136.6 chars/s | 1.5K 21 | 1 | — | 24.1 | 45.7 | — |
|
100
DeepSeek R1
|
273.3 chars/s | 1.4K 2 | 1 | — | — | — | — |
|
101
DeepSeek V3
|
204.1 chars/s | 1.1K 12 | 1 | — | — | — | — |
|
102
Claude 3.5 Sonnet
|
167.6 chars/s | 319 80 | 2 | — | — | — | — |
|
103
Grok-3 (Beta)
|
99.0 chars/s | 142 6 | 3 | — | 73.6 | 63.2 | — |
|
104
GPT-4 Turbo
|
43.7 chars/s | 62 32 | 10 | — | — | — | — |
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.
BenchmarksLiveBench measures broad and coding performance. WebDev Arena is an independent leaderboard for web-development output.
