Live Rankings

AI Model Leaderboard

Comprehensive rankings of AI models based on real-world performance data from the Zip platform. Search across all 168 models.

Top 10 Charts

Intelligence Index

Composite score from real agentic tasks

Speed

Output tokens per second

Price (Blended)

USD per 1M tokens • 7:2:1 ratio

Full Rankings

Showing 101-150 of 168 models

Click column headers to sort
# Model Creator Intelligence Speed Price Popular Type Compare
101 Mistral Large
Mistral AI
0.0 0.0 tok/s $3.20 6.5 Proprietary
102 Mistral Large 2407
Mistral AI
0.0 0.0 tok/s $3.20 6.5 Proprietary
103 Mistral Large 3 2512
Mistral AI
0.0 0.0 tok/s $0.80 7.0 Proprietary
104 Mistral Medium 3
Mistral AI
0.0 0.0 tok/s $0.88 6.5 Proprietary
105 Mistral Medium 3.1
Mistral AI
0.0 0.0 tok/s $0.88 6.5 Proprietary
106 Mistral Medium 3.5
Mistral AI
0.0 0.0 tok/s $3.30 7.0 Proprietary
107 Mistral Small 4
Mistral AI
0.0 0.0 tok/s $0.28 4.0 Proprietary
108 Nano Banana (Gemini 2.5 Flash Image)
Google
0.0 0.0 tok/s $0.96 6.0 Proprietary
109 Nemotron 3 Nano 30B A3B
NVIDIA
0.0 0.0 tok/s $0.10 4.0 Proprietary
110 Nemotron 3 Super
NVIDIA
0.0 0.0 tok/s $0.20 4.5 Proprietary
111 Nemotron 3 Ultra
NVIDIA
0.0 0.0 tok/s $1.10 4.5 Proprietary
112 o1
OpenAI
0.0 0.0 tok/s $28.50 4.0 Proprietary
113 o1-pro
OpenAI
0.0 0.0 tok/s $285.00 4.0 Proprietary
114 o3
OpenAI
0.0 0.0 tok/s $3.80 4.0 Proprietary
115 o3 Deep Research
OpenAI
0.0 0.0 tok/s $19.00 4.0 Proprietary
116 o3 Mini
OpenAI
0.0 0.0 tok/s $2.09 4.0 Proprietary
117 o3 Mini High
OpenAI
0.0 0.0 tok/s $2.09 4.0 Proprietary
118 o3 Pro
OpenAI
0.0 0.0 tok/s $38.00 4.0 Proprietary
119 o4 Mini
OpenAI
0.0 0.0 tok/s $2.09 4.0 Proprietary
120 o4 Mini Deep Research
OpenAI
0.0 0.0 tok/s $3.80 4.0 Proprietary
121 o4 Mini High
OpenAI
0.0 0.0 tok/s $2.09 4.0 Proprietary
122 Qwen Plus 0728
Qwen (Alibaba)
0.0 0.0 tok/s $0.42 4.5 Proprietary
123 Qwen Plus 0728 (thinking)
Qwen (Alibaba)
0.0 0.0 tok/s $0.42 4.5 Proprietary
124 Qwen-Plus
Qwen (Alibaba)
0.0 0.0 tok/s $0.42 4.5 Proprietary
125 Qwen2.5 72B Instruct
Qwen (Alibaba)
0.0 0.0 tok/s $0.37 6.5 Proprietary
126 Qwen2.5 7B Instruct
Qwen (Alibaba)
0.0 0.0 tok/s $0.06 6.5 Proprietary
127 Qwen2.5 Coder 32B Instruct
Qwen (Alibaba)
0.0 0.0 tok/s $0.76 6.5 Proprietary
128 Qwen3 235B A22B Instruct 2507
Qwen (Alibaba)
0.0 0.0 tok/s $0.09 4.0 Proprietary
129 Qwen3 235B A22B Thinking 2507
Qwen (Alibaba)
0.0 0.0 tok/s $0.10 4.0 Proprietary
130 Qwen3 Coder 480B A35B
Qwen (Alibaba)
0.0 0.0 tok/s $0.69 4.5 Proprietary
131 Qwen3 Coder Flash
Qwen (Alibaba)
0.0 0.0 tok/s $0.43 4.5 Proprietary
132 Qwen3 Coder Next
Qwen (Alibaba)
0.0 0.0 tok/s $0.32 4.0 Proprietary
133 Qwen3 Coder Plus
Qwen (Alibaba)
0.0 0.0 tok/s $1.43 4.5 Proprietary
134 Qwen3 Max
Qwen (Alibaba)
0.0 0.0 tok/s $1.72 4.0 Proprietary
135 Qwen3 Max Thinking
Qwen (Alibaba)
0.0 0.0 tok/s $1.72 4.0 Proprietary
136 Qwen3 Next 80B A3B Instruct
Qwen (Alibaba)
0.0 0.0 tok/s $0.39 4.0 Proprietary
137 Qwen3 Next 80B A3B Thinking
Qwen (Alibaba)
0.0 0.0 tok/s $0.30 4.0 Proprietary
138 Qwen3 VL 235B A22B Instruct
Qwen (Alibaba)
0.0 0.0 tok/s $0.40 4.0 Proprietary
139 Qwen3 VL 30B A3B Instruct
Qwen (Alibaba)
0.0 0.0 tok/s $0.25 4.0 Proprietary
140 Qwen3 VL 32B Instruct
Qwen (Alibaba)
0.0 0.0 tok/s $0.20 4.0 Proprietary
141 Qwen3 VL 8B Instruct
Qwen (Alibaba)
0.0 0.0 tok/s $0.21 4.0 Proprietary
142 Qwen3 VL 8B Thinking
Qwen (Alibaba)
0.0 0.0 tok/s $0.49 4.0 Proprietary
143 Qwen3.5 397B A17B
Qwen (Alibaba)
0.0 0.0 tok/s $0.97 4.0 Proprietary
144 Qwen3.5 Plus 2026-02-15
Qwen (Alibaba)
0.0 0.0 tok/s $0.65 4.5 Proprietary
145 Qwen3.5 Plus 2026-04-20
Qwen (Alibaba)
0.0 0.0 tok/s $0.75 4.5 Proprietary
146 Qwen3.5-122B-A10B
Qwen (Alibaba)
0.0 0.0 tok/s $0.81 4.0 Proprietary
147 Qwen3.5-27B
Qwen (Alibaba)
0.0 0.0 tok/s $0.60 4.0 Proprietary
148 Qwen3.5-35B-A3B
Qwen (Alibaba)
0.0 0.0 tok/s $0.40 4.0 Proprietary
149 Qwen3.5-9B
Qwen (Alibaba)
0.0 0.0 tok/s $0.12 4.0 Proprietary
150 Qwen3.5-Flash
Qwen (Alibaba)
0.0 0.0 tok/s $0.12 4.5 Proprietary

How to interpret these rankings

Intelligence

Composite score from real agentic tasks including coding, research, analysis, and planning. Higher is better.

Speed

Output tokens per second using OpenAI tokens as standard measurement. Higher is better.

Price

Blended price per 1M tokens assuming 7:2:1 ratio of cache hit, input, and output. Lower is better.