Model Statistics

Time Period

Weekly Token Usage by Model

Loading chart data...

Below is a list of AI models available on CodingFleet, along with statistics & benchmarks for the selected time period. The statistics are based on actual usage by CodingFleet users.

Legacy models are shown in the list but are grayed out and disabled. These models are no longer available.

The cost of the model is the number of credits required to use the model in a single request. For Unlimited and Elite users, the usage for 1-cost models is unlimited, while others are limited as shown in the pricing page.

Model Avg Speed (chars/s) The average speed of the model in characters per second, across all users utilizing this model. N° Tokens The total number of tokens in both the prompt and the completion combined, across all users utilizing this model. Cost The credit cost of utilizing this model in a request. Models with a cost of 2 or higher are considered premium models. Vote Score The average vote score given to this model by CodingFleet users, where -1 is the lowest score and 1 is the highest. This is displayed only if there are 10 or more votes for the model. LiveBench Coding The average LiveBench coding score (livebench.ai) LiveBench Avg The average LiveBench average score (livebench.ai) WebDev Arena WebDev Arena is an open-source benchmark evaluating AI capabilities in web development (https://web.lmarena.ai/leaderboard)
Claude Sonnet 4.5 Thinking
151.3 3.7B 0 8 0.6 80.4 78.3 1397.0
Claude Opus 4.6 Thinking
129.2 2.5B 0 17 1.0 78.2 76.3 1547.0
Claude Haiku 4.5 Thinking
243.8 2.4B 0 1 0.1 72.8 71.4 -
DeepSeek V4 Flash
341.8 2.4B 0 1 - - - -
Claude Sonnet 4.6 Thinking
138.9 2.3B 0 10 1.0 80.0 75.3 -
DeepSeek V4 Pro Max
88.9 2.1B 0 1 - - - -
Claude Opus 4.5 Thinking
177.1 1.9B 0 17 - 79.7 79.8 1518.0
GPT-5 Mini
148.1 1.9B 0 1 0.4 - - -
GPT-5.2 Thinking High
98.6 1.9B 0 6 0.5 76.1 73.6 1485.0
Gemini 3 Flash
292.1 1.5B 0 1 0.3 73.9 73.6 1465.0
GPT-5.4 Thinking xHigh
106.4 1.4B 0 11 - 77.5 80.3 1458.0
DeepSeek V4 Pro
109.7 1.3B 0 1 - - - -
Claude Haiku 4.5
380.1 1.3B 0 1 0.5 - - -
Claude 4 Sonnet Thinking
147.8 1.1B 0 7 0.6 73.6 72.1 1381.8
Claude Sonnet 4.5
190.2 896.1M 0 7 0.2 - - -
Claude Opus 4.7 Thinking
134.6 894.9M 0 17 - 82.1 76.9 1503.0
GPT-5 Thinking High
71.1 872.3M 0 5 1.0 75.3 78.6 1480.5
GPT-5.4 Mini
438.6 846.0M 0 1 - - - -
Claude Sonnet 4.6
172.9 756.3M 1 9 1.0 - - -
DeepSeek V3.2
93.6 569.6M 1 1 0.4 68.5 62.6 -
Gemini 3.1 Pro
185.1 551.2M 4 4 1.0 76.5 79.9 1500.0
GPT-5 Thinking
90.8 517.5M 4 5 - 73.3 76.5 -
GPT-5.2 Codex High
102.6 506.3M 5 7 - 83.6 74.3 -
GPT-5.1 Codex Mini
263.8 484.7M 5 1 - 71.8 69.8 1248.0
Claude 4 Sonnet
189.5 480.3M 2 6 0.8 77.5 69.7 1381.8
GPT-5.2
204.9 461.3M 5 4 1.0 - - -
Gemini 3 Pro
159.1 410.7M 6 4 1.0 74.6 79.7 1481.0
Claude Opus 4.8 Thinking
136.9 397.0M 6 17 - - - -
GPT-5.4 Thinking High
158.5 389.8M 6 9 1.0 - - 1481.0
GPT-5.1 Thinking High
141.2 370.1M 6 5 - 72.5 72.5 1395.0
GPT-4.1
214.2 346.4M 7 6 - 73.2 63.0 1256.5
Gemini 2.5 Flash
357.5 341.4M 6 1 0.3 60.3 69.9 1304.9
Gemini 2.5 Pro
166.0 340.2M 4 4 0.6 72.9 79.0 1409.1
GPT-5.3 Codex xHigh
92.5 317.7M 7 9 - - - -
GPT-5.2 Thinking
144.6 292.9M 7 5 - - - -
GPT-5 Mini High
77.9 284.5M 7 2 1.0 66.4 72.2 -
GPT-4.1 mini
208.5 282.3M 5 1 0.1 72.1 59.1 1194.4
GPT-5.2 Thinking xHigh
60.8 269.1M 6 8 - - - -
Claude 3.5 Haiku
202.3 262.7M 20 1 - 53.2 45.0 1133.8
GPT-5.4 Mini High
180.4 259.7M 5 1 - - - -
GPT-5.1 Thinking
168.4 243.4M 5 5 1.0 - - 1395.0
GLM 5.1
113.4 223.3M 8 1 - - - -
GPT-5.4 Mini xHigh
63.2 217.9M 8 2 - - - -
GPT-5
200.8 186.6M 8 3 1.0 72.5 75.3 -
GPT-5.4 Thinking
188.3 182.8M 8 8 1.0 - - -
Qwen 3.6 Plus
72.3 170.1M 9 1 - - - -
MiniMax M2.7
187.8 161.9M 9 1 - - - -
GPT-5.4
261.5 146.3M 9 6 - - - -
Kimi K2.5
93.4 139.3M 9 1 - 77.9 69.1 -
GPT-5.5
204.7 136.9M 10 13 - - - -
Claude Opus 4.7
173.8 132.5M 10 15 - - - 1494.0
GPT-5.3 Codex High
124.4 124.2M 10 7 - - - -
Claude 4.1 Opus Thinking
111.7 122.4M 10 60 - 74.0 73.5 1476.5
GLM 5
182.5 119.5M 11 1 - 73.6 68.9 1456.0
GPT-5.5 Thinking High
131.9 106.2M 14 18 - - - -
OpenAI o3-high
102.9 99.3M 12 5 1.0 76.7 74.6 1188.3
GPT-5.1
267.8 93.0M 13 3 - - - -
Gemini 3.5 Flash
286.6 92.5M 13 3 1.0 - - -
GLM 5 Turbo
164.0 86.2M 13 1 - - - -
GPT-5.2 Codex
178.4 84.1M 13 5 - 83.6 74.3 -
Grok-4.1 Fast
165.3 80.0M 14 1 - - - -
Grok-4 Fast
373.6 76.7M 14 1 0.4 - - -
GPT-5.1 Codex Max High
188.7 74.1M 14 5 - 81.4 75.2 -
OpenAI o3
131.5 66.1M 3 4 - 77.9 72.0 1188.1
MiniMax M3
186.0 66.0M 16 1 - - - -
Qwen 3.5 Plus
178.4 63.5M 16 1 - - - -
DeepSeek V4 Flash Max
177.1 60.3M 16 1 - - - -
Qwen 3.7 Max
131.6 59.1M 17 3 - - - -
Claude Opus 4.6
119.5 57.6M 17 15 - 78.2 76.3 1504.0
GPT-5.1 Codex Mini High
221.7 56.5M 18 1 - 71.8 69.8 1248.0
GPT-5.2 Codex xHigh
95.6 55.9M 18 9 - 83.6 74.3 -
GPT-5.3 Codex
169.1 55.4M 18 5 - - - -
Kimi K2.6
59.0 52.7M 18 1 - - - -
MiMo V2.5 Pro
171.3 51.5M 18 1 - - - -
GLM 5V Turbo
220.0 47.4M 18 1 - - - -
OpenAI o4-mini
178.6 45.6M 17 2 - - - 1095.1
Qwen 3.5 Flash
330.9 44.5M 17 1 - - - -
DeepSeek V3.2 Thinking
47.0 44.0M 2 1 - 64.6 66.6 -
MiniMax M2.5
143.1 39.4M 20 1 - 70.7 60.1 -
Grok Build 0.1
161.6 36.8M 20 1 - - - -
Gemini 2.0 Flash
547.6 36.2M 41 1 - 64.7 60.1 1035.2
Claude Opus 4.5
174.9 34.0M 20 15 - 77.5 76.0 1484.0
Claude Fable 5 Thinking
140.3 29.2M 21 34 - - - -
GPT-5.5 Thinking
210.1 27.2M 21 16 - - - -
Qwen 3.6 Flash
195.7 27.1M 21 1 - - - -
GPT-5.5 Thinking xHigh
121.0 26.2M 21 22 - 82.5 80.7 -
GPT-5.1 Codex Max
220.8 24.5M 21 4 - 81.4 75.2 -
Qwen3 235B A22B
159.2 23.8M 21 1 - 66.4 64.9 -
Claude 4 Opus Thinking
129.0 23.3M 12 60 - 73.3 72.9 1405.5
Claude 3.7 Sonnet
203.2 23.3M 51 6 - 74.3 58.5 1356.7
MiMo V2 Pro
302.5 18.6M 21 1 - - - -
Claude Opus 4.8
154.5 18.4M 21 15 - - - -
Qwen 3.6 Max Preview
49.6 16.7M 22 4 - - - -
Grok-4
129.1 16.7M 20 5 - 71.3 72.1 -
Claude 3.7 Sonnet Thinking
131.9 16.2M 47 7 - 73.2 67.4 1356.7
Claude 4.1 Opus
129.2 16.2M 21 50 - - - -
Llama 4 Maverick
316.2 15.8M 6 1 - 54.2 55.2 998.5
Grok-4.20 Beta
626.2 13.6M 22 4 - - - -
OpenAI o4-mini-high
117.2 13.5M 20 2 - - - -
GLM 4.6
159.0 13.0M 21 1 - - - -
GPT-5 Pro
35.0 12.9M 21 70 - 72.1 78.7 -
Mistral Medium 3
264.0 8.0M 21 1 - 61.5 56.6 1160.1
Claude 4 Opus
140.9 7.2M 16 50 - 72.9 71.5 1405.5
GLM 4.7
91.8 7.2M 22 1 - 73.1 58.1 -
GPT-4o
278.6 6.2M 75 2 - - - -
GPT-5.2 Codex
225.7 5.2M 22 8 - - - -
Codestral (2508)
423.0 4.5M 22 1 - - - -
Grok-3 Mini (Beta)
357.1 3.7M 16 1 - 54.5 70.3 -
GPT-4o Mini
170.3 3.3M 82 1 - 43.2 41.3 -
Qwen3 Coder
293.2 3.3M 22 2 - 73.2 60.5 -
Kimi K2 Thinking
138.5 3.0M 24 1 - - - -
Grok-4.20
700.7 2.8M 24 4 - - - -
Kimi K2.7 Code
114.3 1.7M 25 1 - - - -
Kimi K2 (0905)
184.7 1.6M 25 1 - 71.8 62.7 -
Grok-4.3
326.6 1.2M 25 3 - - - -
Mistral Medium 3.5
317.2 1.1M 25 2 - - - -
Mistral Large 3
243.1 743.2K 25 1 - 62.9 50.3 -
Grok-3 (Beta)
304.0 702.3K 13 3 - 73.6 63.2 -
Llama 3.1 405B
92.4 373.5K 24 2 - 42.7 52.4 813.7
Qwen 3.7 Plus
63.7 308.4K 23 1 - - - -
Qwen2.5-Coder 32B
335.2 198.6K 9 1 - 56.9 46.2 904.1
Llama 3.3 70B
861.3 49.5K 24 1 - 24.1 45.7 -
GPT-3.5 Turbo
85.0 10.2K 74 1 - - - -
DeepSeek R1
273.3 1.4K 3 1 - - - -
DeepSeek V3
204.1 1.1K 9 1 - - - -
Claude 3.5 Sonnet
167.6 319 104 2 - - - -
GPT-4 Turbo
43.7 62 40 10 - - - -