AI Model Leaderboard

Agentic work ranking, Model families, sorted by Overall
Rank Model Provider Weights Overall Coding Agents Reasoning Math Knowledge Cost
15 Kimi K3.1 Pro Moonshot AI Open 62.4 61.2 62.6 63.9 62.3 60.5 $8.00
18 DeepSeek V4.1 Flash 1017 DeepSeek Open 62.2 62.9 61.6 63.4 60.7 55.4 $0.26
27 GLM-5.3 Zhipu AI Open 60.6 60.7 60.8 59.3 58.1 56.6 $1.94
34 MiMo-V2.6-Pro Xiaomi Open 59.9 59.6 60.2 59.2 59.9 62.0 $0.54
35 Kimi K3 Moonshot AI Open 59.9 59.5 59.4 62.1 60.2 58.3 $6.00
38 MiniMax-M3.1-Flash MiniMax Open 59.4 61.0 60.1 53.9 –No results 57.2 $0.26
39 MiMo-V2.6-Flash Xiaomi Open 59.4 57.4 60.0 60.4 59.2 58.7 $0.18
41 GLM-5.3-Flash Zhipu AI Open 59.3 58.9 59.3 59.5 56.3 55.8 $0.19
42 DeepSeek V4.1 Flash DeepSeek Open 59.2 60.0 58.3 61.5 58.8 55.3 $0.33
43 Step 5 Preview StepFun Open 59.2 60.1 58.9 59.0 57.3 59.6 $1.53
46 DeepSeek V4 Pro 0813 DeepSeek Open 58.9 58.4 58.5 61.3 58.7 57.2 $0.99
49 Mistral Large 4 Preview Mistral Open 58.6 60.2 58.1 57.8 57.3 45.1 –No price
53 DeepSeek V4 Flash 0731 DeepSeek Open 58.3 55.2 59.1 60.1 57.5 53.1 $0.19
58 Hy4 preview Tencent Open 57.9 58.0 58.0 57.1 60.5 61.3 $1.25
59 Muse Spark Open Meta Open 57.6 58.4 57.0 58.8 59.6 58.9 $2.00
61 GLM-5.2 Zhipu AI Open 57.0 56.3 57.5 56.5 56.8 53.6 $1.94
63 Qwen3.8 27B Alibaba Open 56.8 57.7 56.3 57.0 54.4 52.6 $0.83
65 Kimi K2.7 Code Moonshot AI Open 56.6 55.3 57.2 56.1 56.5 52.0 $1.71
68 DeepSeek V4 Pro DeepSeek Open 56.4 54.5 56.9 58.0 54.0 54.4 $2.06
69 Beam 1.0 Reflection Open 56.3 54.8 56.9 56.8 54.7 55.0 –No price
70 Kimi K2.6 Moonshot AI Open 56.0 56.7 55.1 58.4 56.7 51.9 $1.71
73 GLM-5.1 Zhipu AI Open 55.8 53.4 56.8 55.9 54.7 53.3 $1.57
80 MiniMax-M3 MiniMax Open 54.4 52.8 55.0 54.7 52.4 51.6 $0.53
82 Nemotron 3 Ultra 550B A55B NVIDIA Open 54.0 54.9 53.2 55.2 –No results 50.7 $0.000
83 Inkling Thinking Machines Open 53.7 52.4 53.6 56.2 51.7 53.7 $2.57
86 MiMo-V2.5-Pro Xiaomi Open 53.5 54.0 53.8 51.7 55.2 49.4 $0.54
87 Inkling Small Thinking Machines Open 53.4 53.9 52.3 56.9 54.9 49.8 $0.53
88 MiMo-V2.5 Xiaomi Open 53.3 51.8 54.3 52.0 54.4 45.6 $0.18
89 Kimi K2.5 Moonshot AI Open 53.1 54.4 52.5 53.4 53.5 51.9 $1.20
90 Nemotron 3.5 Super VL 120B A12B NVIDIA Open 53.1 54.9 53.7 47.4 –No results 43.5 $0.000
98 GLM-5 Zhipu AI Open 52.0 53.5 51.2 52.7 50.9 52.8 $1.12
100 Qwen3.5 397B-A17B Alibaba Open 51.8 –No results 51.7 51.9 52.3 –No results $1.35
101 MiniMax-M2.7 MiniMax Open 51.6 54.2 51.3 48.7 49.7 43.7 $0.53
104 Nemotron 3 Ultra NVIDIA Open 51.1 48.8 51.8 51.9 50.3 –No results –No price
105 DeepSeek V3.2 DeepSeek Open 51.0 52.5 50.4 50.5 51.5 50.8 $0.33
109 GLM-4.7 Zhipu AI Open 49.9 52.5 48.6 50.7 46.6 49.5 $0.86
110 MiniMax-M2.1 MiniMax Open 49.6 54.0 48.5 46.4 –No results 54.7 $0.53
112 MiniMax-M2.5 MiniMax Open 49.4 53.3 47.7 49.7 50.4 43.4 $0.53
118 Gemma 4 31B IT Google Open 48.4 45.7 49.1 50.5 49.2 38.7 $0.21
123 DeepSeek-V3.2-Exp DeepSeek Open 48.0 48.7 47.5 48.8 –No results –No results –No price
124 Kimi K2 Thinking Moonshot AI Open 47.9 48.0 47.6 49.3 50.1 44.8 $1.08
125 GLM-4.6 Zhipu AI Open 47.6 48.6 47.8 45.2 45.8 46.5 $1.00
128 MiniMax-M2 MiniMax Open 46.2 –No results 46.7 44.2 –No results –No results $0.53
129 Kimi K2 Instruct Moonshot AI Open 46.1 46.6 46.4 44.2 –No results 42.5 $0.88
130 Laguna XS.2 Poolside Open 46.0 50.0 46.0 39.2 45.4 26.9 $0.000
132 Laguna M.1 Poolside Open 45.9 50.3 48.6 27.5 45.4 29.7 $0.000
134 Qwen3.6 35B-A3B Alibaba Open 45.6 44.1 45.1 49.8 49.9 –No results $0.36
140 DeepSeek R1 0528 DeepSeek Open 44.6 48.2 42.6 46.4 49.7 –No results $1.01
141 Qwen3 235B-A22B Instruct 2507 Alibaba Open 44.4 44.8 44.3 44.4 –No results –No results $0.31
143 DeepSeek-R1 DeepSeek Open 44.2 45.3 43.3 45.9 46.6 48.0 $2.36
146 GPT OSS 120B OpenAI Open 43.0 44.1 42.1 44.7 53.5 42.2 $0.26
147 Command A Plus Cohere Open 43.0 44.8 42.8 40.8 –No results –No results $4.38
149 DeepSeek V3 0324 DeepSeek Open 42.1 44.7 41.0 41.7 41.2 42.6 $0.50
150 Qwen3 32B Alibaba Open 42.1 39.8 42.9 42.5 48.0 –No results $0.26
151 Llama-3.2-90B-Vision-Instruct Meta Open 42.0 –No results 44.0 34.2 32.6 –No results $0.000
153 DeepSeek-V3 DeepSeek Open 40.3 41.8 39.8 39.7 39.0 35.6 $0.51
156 Qwen3-14B Alibaba Open 39.6 37.9 39.7 42.3 47.9 –No results –No price
158 Command A Cohere Open 38.9 33.6 42.0 35.7 –No results 30.6 $4.38
159 Qwen3.5 9B Alibaba Open 38.8 35.7 38.1 46.5 46.9 –No results $0.14
161 GPT OSS 20B OpenAI Open 38.0 48.7 31.8 45.1 47.7 33.2 $0.13
163 Mistral Large 2.1 Mistral Open 37.3 34.4 38.5 37.2 35.1 31.1 $3.00
165 Qwen3 8B Alibaba Open 37.1 27.6 40.3 40.4 46.1 –No results $0.098
166 Qwen3 235B-A22B Thinking 2507 Alibaba Open 37.1 47.5 30.6 45.8 48.0 53.4 $0.95
167 Llama 4 Maverick Meta Open 37.0 31.9 38.0 41.4 38.5 39.3 –No price
169 Mistral Small 3.2 Mistral Open 36.6 32.2 38.0 38.6 41.8 –No results $0.22
170 Llama-3.3-70B-Instruct Meta Open 35.5 31.8 36.4 38.1 33.7 –No results $0.72
172 Qwen2.5-VL 72B Instruct Alibaba Open 34.8 –No results 34.2 37.2 37.0 –No results $1.01
174 Phi-4 Microsoft Open 34.5 –No results 33.1 40.2 38.0 –No results –No price
177 Mistral Nemo Mistral Open 33.0 –No results 33.9 29.3 26.0 –No results $0.11
178 Llama 4 Scout Meta Open 32.3 25.9 33.7 37.7 35.8 –No results –No price
179 Gemma 3 27B IT Google Open 32.2 23.4 34.4 38.1 40.1 –No results $0.16
182 Gemma 3 12B IT Google Open 31.1 18.7 34.9 36.5 38.7 –No results $0.075
184 Gemma 3 4B IT Google Open 28.5 –No results 28.8 27.3 35.1 –No results $0.063
186 Llama-3.1-8B-Instruct Meta Open 27.8 12.9 32.6 33.3 29.6 –No results $0.058
188 Llama 3.2 1B Instruct Meta Open 22.5 –No results 21.5 26.4 24.3 –No results $0.071