AI Model Leaderboard

Coding ranking, Model families, sorted by Overall
Rank Model Provider Weights Overall Coding Agents Reasoning Math Knowledge Cost
12 DeepSeek V4.1 Flash 1017 DeepSeek Open 62.5 62.9 61.6 63.4 60.6 55.4 $0.26
17 Kimi K3.1 Pro Moonshot AI Open 61.6 61.1 62.6 63.8 62.2 60.5 $4.00
25 GLM-5.3 Zhipu AI Open 60.2 60.6 60.8 59.3 58.1 56.6 $1.94
28 DeepSeek V4.1 Flash DeepSeek Open 59.9 60.0 58.3 61.4 58.8 55.3 $0.33
31 Kimi K3 Moonshot AI Open 59.7 59.4 59.4 62.1 60.1 58.3 $6.00
33 MiMo-V2.6-Pro Xiaomi Open 59.6 59.5 60.2 59.1 59.9 62.0 $0.54
35 Mistral Large 4 Preview Mistral Open 59.5 60.2 58.1 57.7 57.3 45.1 –No price
36 MiniMax-M3.1-Flash MiniMax Open 59.4 60.9 60.1 53.9 –No results 57.2 $0.26
39 Step 5 Preview StepFun Open 59.1 60.1 58.9 59.0 57.3 59.6 $1.53
40 DeepSeek V4 Pro 0813 DeepSeek Open 58.9 58.3 58.5 61.3 58.7 57.2 $0.99
46 MiMo-V2.6-Flash Xiaomi Open 58.4 57.3 60.0 60.4 59.2 58.7 $0.18
47 GLM-5.3-Flash Zhipu AI Open 58.4 58.9 59.3 59.5 56.3 55.8 $0.49
51 Hy4 preview Tencent Open 57.9 58.0 58.0 57.1 60.5 61.3 $1.25
56 Muse Spark Open Meta Open 57.2 58.4 57.0 58.8 59.6 58.9 $2.00
58 Qwen3.8 27B Alibaba Open 57.1 57.7 56.3 57.0 54.4 52.6 $0.83
59 DeepSeek V4 Flash 0731 DeepSeek Open 56.8 55.2 59.1 60.1 57.5 53.1 $0.19
61 GLM-5.2 Zhipu AI Open 56.3 56.2 57.5 56.4 56.8 53.6 $1.94
65 Beam 1.0 Reflection Open 55.5 54.8 56.9 56.8 54.7 55.0 –No price
66 Kimi K2.6 Moonshot AI Open 55.5 56.6 55.1 58.3 56.7 51.9 $1.71
68 Kimi K2.7 Code Moonshot AI Open 55.2 55.3 57.2 56.1 56.5 52.0 $1.71
71 DeepSeek V4 Pro DeepSeek Open 55.0 54.4 56.9 58.0 54.0 54.4 $2.06
81 GLM-5.1 Zhipu AI Open 53.6 53.4 56.8 55.8 54.7 53.3 $1.57
86 MiniMax-M3 MiniMax Open 53.2 52.8 55.0 54.7 52.4 51.6 $0.53
87 MiMo-V2.5-Pro Xiaomi Open 53.0 54.0 53.8 51.6 55.2 49.4 $0.54
88 Inkling Small Thinking Machines Open 52.5 53.9 52.3 56.9 54.9 49.8 $0.53
89 Kimi K2.5 Moonshot AI Open 52.5 54.4 52.5 53.4 53.5 51.9 $1.20
90 Nemotron 3 Ultra 550B A55B NVIDIA Open 52.4 54.9 53.2 55.2 –No results 50.7 $0.000
91 DeepSeek V4 Flash DeepSeek Open 52.3 50.7 –No results 55.9 55.7 –No results $0.18
93 MiMo-V2.5 Xiaomi Open 52.1 51.8 54.3 52.0 54.4 45.6 $0.18
94 GLM-5 Zhipu AI Open 51.9 53.5 51.2 52.7 50.9 52.8 $1.12
95 Inkling Thinking Machines Open 51.9 52.4 53.6 56.2 51.8 53.7 $2.57
98 MiniMax-M2.1 MiniMax Open 51.8 54.0 48.5 46.4 –No results 54.7 $0.53
104 MiniMax-M2.7 MiniMax Open 51.3 54.2 51.3 48.6 49.7 43.7 $0.53
106 Nemotron 3.5 Super VL 120B A12B NVIDIA Open 51.2 54.9 53.7 47.3 –No results 43.5 $0.000
107 GLM-4.7 Zhipu AI Open 50.5 52.4 48.6 50.6 46.6 49.5 $0.86
110 MiniMax-M2.5 MiniMax Open 50.4 53.3 47.7 49.7 50.4 43.4 $0.53
111 Nemotron 3 Ultra NVIDIA Open 49.9 48.8 51.8 51.9 50.3 –No results –No price
113 DeepSeek V3.2 DeepSeek Open 49.7 52.5 50.4 50.5 51.5 50.8 $0.33
119 Muse Glimmer Meta Open 48.7 50.7 –No results 50.1 –No results –No results –No price
120 Kimi K2 Thinking Moonshot AI Open 48.0 48.0 47.6 49.2 50.1 44.8 $1.08
130 Qwen3.6 27B Alibaba Open 46.9 48.0 –No results 47.5 53.1 –No results $1.03
131 Step 3.7 Flash StepFun Open 46.9 46.2 –No results 50.4 52.8 –No results $0.45
133 DeepSeek R1 0528 DeepSeek Open 46.7 48.2 42.6 46.3 49.7 –No results $1.01
134 GLM-4.5 Zhipu AI Open 46.7 46.6 –No results 46.8 –No results 42.9 $1.00
135 Gemma 4 31B IT Google Open 46.6 45.7 49.1 50.5 49.2 38.7 $0.21
138 DeepSeek-V3.2-Exp DeepSeek Open 46.4 48.7 47.5 48.8 –No results –No results –No price
139 Laguna M.1 Poolside Open 46.4 50.2 48.6 27.4 45.4 29.7 $0.000
140 Laguna XS.2 Poolside Open 46.3 50.0 46.0 39.2 45.4 26.9 $0.000
141 Kimi K2 Instruct Moonshot AI Open 46.3 46.6 46.4 44.1 –No results 42.5 $0.88
142 GLM-4.6 Zhipu AI Open 46.2 48.6 47.8 45.1 45.8 46.5 $1.00
145 Qwen3-Coder 480B-A35B Instruct Alibaba Open 45.1 47.5 45.9 –No results –No results –No results $0.62
147 Qwen3.6 35B-A3B Alibaba Open 45.0 44.1 45.1 49.7 49.9 –No results $0.36
148 Gemma 4 26B A4B IT Google Open 45.0 46.2 –No results 44.4 51.3 –No results $0.20
149 Qwen3 235B-A22B Alibaba Open 44.9 45.0 –No results 44.4 39.0 45.0 $0.50
150 DeepSeek-R1 DeepSeek Open 44.9 45.3 43.3 45.9 46.6 48.0 $2.36
153 DeepSeek-V3.1-Terminus DeepSeek Open 44.8 44.3 –No results 47.5 –No results –No results –No price
154 Qwen3 235B-A22B Instruct 2507 Alibaba Open 44.6 44.8 44.3 44.3 –No results –No results $0.31
155 Mistral Medium 3.5 Mistral Open 44.4 45.1 –No results 40.8 52.4 –No results $3.14
156 GPT OSS 20B OpenAI Open 44.3 48.7 31.8 45.1 47.7 33.2 $0.13
158 Trinity Large Thinking Arcee AI Open 43.9 46.8 –No results 45.1 –No results –No results $0.41
159 Command A Plus Cohere Open 43.9 44.8 42.8 40.8 –No results –No results $4.38
160 Magistral Small 1.2 Mistral Open 43.8 44.6 –No results 39.4 41.4 23.7 $0.75
161 GPT OSS 120B OpenAI Open 43.7 44.1 42.1 44.7 53.5 42.2 $0.26
163 DeepSeek V3 0324 DeepSeek Open 43.5 44.7 41.0 41.6 41.3 42.6 $0.50
164 Qwen3 235B-A22B Thinking 2507 Alibaba Open 43.3 47.5 30.6 45.8 48.0 53.4 $0.95
165 Nemotron 3 Super NVIDIA Open 43.1 42.4 –No results 47.2 –No results –No results –No price
166 Devstral 2 Mistral Open 43.0 46.6 –No results –No results –No results –No results $0.80
168 Qwen3.5 122B-A10B Alibaba Open 42.8 42.0 –No results 49.5 –No results –No results $0.79
176 Mistral Large 3 Mistral Open 41.2 43.4 –No results 41.9 –No results 43.0 $0.75
177 DeepSeek-V3 DeepSeek Open 41.1 41.8 39.8 39.7 39.1 35.6 $0.51
178 Qwen3 32B Alibaba Open 40.8 39.8 42.9 42.5 48.0 –No results $0.26
180 Qwen3-30B-A3B-Thinking (Jul 2025) Alibaba Open 40.1 39.4 –No results 44.0 48.6 –No results –No price
181 Qwen3.5 35B-A3B Alibaba Open 39.2 39.1 –No results 48.1 48.7 –No results $0.36
183 Qwen3-14B Alibaba Open 38.9 37.9 39.7 42.3 47.9 –No results –No price
189 Qwen3.5 9B Alibaba Open 37.6 35.7 38.1 46.5 47.0 –No results $0.14
191 Command A Cohere Open 35.8 33.6 42.0 35.7 –No results 30.6 $4.38
192 Mistral Large 2.1 Mistral Open 35.7 34.4 38.5 37.2 35.1 31.1 $3.00
197 Llama 4 Maverick Meta Open 34.4 31.9 38.0 41.4 38.5 39.3 –No price
198 Mistral Small 3.2 Mistral Open 34.3 32.2 38.0 38.6 41.8 –No results $0.22
199 MiMo-V2-Flash Xiaomi Open 34.2 31.7 –No results 40.8 –No results –No results $0.15
201 Llama-3.3-70B-Instruct Meta Open 33.6 31.8 36.4 38.1 33.8 –No results $0.72
202 Mistral Small 3.1 Mistral Open 33.5 32.7 –No results 37.8 34.6 27.4 –No price
204 Qwen3 8B Alibaba Open 32.1 27.6 40.3 40.3 46.2 –No results $0.098
205 Llama 4 Scout Meta Open 29.1 25.9 33.7 37.6 35.9 –No results –No price
206 Gemma 3 27B IT Google Open 27.7 23.4 34.4 38.1 40.1 –No results $0.16
208 Gemma 3 12B IT Google Open 24.6 18.7 34.9 36.4 38.7 –No results $0.075
209 Llama-3.1-8B-Instruct Meta Open 20.0 12.9 32.6 33.3 29.6 –No results $0.058