AllBenched

AI Model Leaderboard

Rank by Balanced
All providers
All weights
Reset
Rank Model Provider Weights Overall Coding Agents Reasoning Math Knowledge Cost
237 Llama 3.2 1B Instruct Meta Open 21.5 – 21.5 26.3 24.4 – $0.071
236 Ministral 8B Instruct Mistral Open 25.3 – 21.9 28.0 27.7 – –
235 Llama-3.1-8B-Instruct Meta Open 25.4 12.9 32.6 33.3 29.6 – $0.058
234 GPT-3.5-turbo OpenAI 25.6 – 21.6 30.1 29.9 – $0.75
233 mistral-small-2402 Unknown 28.0 23.2 – 37.5 – 25.9 –
232 Gemma 3 4B IT Google Open 31.1 – 28.8 27.3 35.1 – $0.063
231 Mistral Nemo Mistral Open 31.2 – 33.9 29.3 26.0 – $0.11
230 Qwen2-72B Alibaba Open 31.2 – 29.3 33.9 33.4 – –
229 Gemma 3 12B IT Google Open 31.4 18.7 34.9 36.4 38.7 – $0.075
228 GPT-4 OpenAI 31.5 – 30.6 34.3 29.1 – $37.50
227 GPT-4o mini OpenAI 32.1 21.5 36.9 36.8 34.7 32.9 $0.26
226 Llama 4 Scout Meta Open 32.7 25.9 33.7 37.6 35.9 – –
225 Mistral Small 3.1 Mistral Open 33.8 32.7 – 37.8 34.6 27.4 –
224 Gemma 3 27B IT Google Open 34.1 23.4 34.4 38.1 40.1 – $0.16
223 Claude 3 Opus Anthropic 34.4 – 29.2 38.0 33.1 40.5 –
222 Solar Pro 3 Upstage 34.5 31.1 – 40.8 – – $0.25
221 GPT-4 Turbo OpenAI 34.5 – 30.4 37.5 34.2 – $15.00
220 Gemini 1.5 Flash (Sep 2024) Google 34.7 34.3 34.4 36.1 36.9 27.0 –
219 GPT-4.1 nano OpenAI 34.8 31.4 36.1 36.8 39.5 31.0 $0.18
218 Llama-3.3-70B-Instruct Meta Open 35.0 31.8 36.4 38.1 33.8 – $0.72
217 Phi-4 Microsoft Open 35.0 – 33.1 40.2 38.0 – –
216 Cohere Command A Cohere Open 35.3 29.3 – 40.8 – – –
215 Claude Haiku 3.5 Anthropic 35.5 35.0 38.5 36.1 34.1 25.6 $1.60
214 Mistral Large 2.1 Mistral Open 35.7 34.4 38.5 37.2 35.1 31.1 $3.00
213 Qwen2.5-VL 72B Instruct Alibaba Open 35.8 – 34.2 37.1 37.1 – $1.01
212 GPT-4o (2024-11-20) OpenAI 36.3 34.2 – 39.8 34.8 32.9 $4.38
211 Grok-2 (Dec 2024) xAI 36.6 35.0 – 38.2 37.0 37.5 –
210 Qwen3 8B Alibaba Open 36.6 27.6 40.3 40.3 46.2 – $0.098
209 Command A Cohere Open 36.7 33.6 42.0 35.7 – 30.6 $4.38
208 Llama-3.2-90B-Vision-Instruct Meta Open 36.9 – 44.0 34.1 32.6 – $0.000
207 Llama 4 Maverick Meta Open 37.0 31.9 38.0 41.4 38.5 39.3 –
206 Mistral Small 3.2 Mistral Open 37.5 32.2 38.0 38.6 41.8 – $0.22
205 Llama-3.1-70B-Instruct Meta Open 37.5 – 44.3 35.3 32.7 – $0.72
204 MiMo-V2-Flash Xiaomi Open 37.7 31.7 – 40.8 – – $0.15
203 GPT-4o (2024-08-06) OpenAI 37.7 34.4 – 39.3 34.3 44.4 $4.38
202 Qwen Max Alibaba 38.0 33.9 – 39.9 38.4 – $2.80
201 GPT-4o (2024-05-13) OpenAI 38.1 – 37.8 37.2 35.2 – $7.50
200 Gemini 2.0 Flash Thinking (Jan 2025) Google 38.2 32.5 – 40.8 46.4 40.6 –
199 Gemini 1.5 Pro (Sept 2024) Google 39.2 36.3 39.7 41.6 39.6 37.4 –
198 Claude 3.5 Sonnet Anthropic 39.2 – 35.7 41.0 37.5 – –
197 Magistral Small 1.2 Mistral Open 39.4 44.6 – 39.4 41.4 23.7 $0.75
196 Mistral Medium 3 Mistral 39.6 37.5 38.2 41.2 39.5 37.3 $0.80
195 QwQ 32B Alibaba Open 39.6 33.6 – 43.6 46.7 – $0.75
194 Gemini 2.0 Pro Google 40.1 38.4 – 41.2 42.7 – –
193 DeepSeek-V3 DeepSeek Open 40.1 41.8 39.8 39.7 39.1 35.6 $0.51
192 o1-mini OpenAI 40.1 37.6 – 42.6 43.3 – –
191 X-Ai/Grok-4-Fast-Non-Reasoning xAI 40.2 38.0 – 42.1 – 31.8 $0.28
190 Qwen3.5 9B Alibaba Open 40.3 35.7 38.1 46.5 47.0 – $0.14
189 Gemini 2.0 Flash Google 40.5 37.0 – 42.5 41.5 39.8 $0.18
188 Qwen3-14B Alibaba Open 40.5 37.9 39.7 42.3 47.9 – –
187 GPT OSS 20B OpenAI Open 40.6 48.7 31.8 45.1 47.7 33.2 $0.13
186 Claude Sonnet 3.5 v2 Anthropic 41.8 43.2 39.9 42.0 39.1 36.7 $6.00
185 Mistral Medium 3.1 Mistral 42.0 38.8 – 41.1 – – $0.80
184 Magistral Medium 1.2 Mistral 42.1 47.4 – 41.5 – 30.0 –
183 o1-preview OpenAI 42.2 – 39.0 43.5 42.0 – –
182 Qwen3 30B-A3B Instruct 2507 Alibaba Open 42.2 – 39.8 39.7 47.2 – $0.15
181 Qwen3 32B Alibaba Open 42.2 39.8 42.9 42.5 48.0 – $0.26
180 Mercury 2 Inception 42.3 44.9 – 43.8 – – $0.38
179 Laguna M.1 Poolside Open 42.4 50.2 48.6 27.4 45.4 29.7 $0.000
178 DeepSeek V3 0324 DeepSeek Open 42.5 44.7 41.0 41.6 41.3 42.6 $0.50
177 GPT-4.1 mini OpenAI 42.6 42.1 43.6 40.7 44.1 40.2 $0.70
176 Qwen3-30B-A3B-Thinking (Jul 2025) Alibaba Open 42.6 39.4 – 44.0 48.6 – –
175 Mistral Large 3 Mistral Open 43.0 43.4 – 41.9 – 43.0 $0.75
174 Command A Plus Cohere Open 43.1 44.8 42.8 40.8 – – $4.38
173 GPT-4.5 OpenAI 43.2 40.9 – 44.0 41.8 38.9 –
172 Laguna XS.2 Poolside Open 43.2 50.0 46.0 39.2 45.4 26.9 $0.000
171 Grok 4.1 Fast xAI 43.3 36.6 48.0 47.0 50.4 37.2 $0.28
170 Qwen3.5 35B-A3B Alibaba Open 43.3 39.1 – 48.1 48.7 – $0.36
169 GLM-4.5-Air Zhipu AI Open 43.4 44.9 – 40.8 – 42.6 $0.31
168 x-AI/Grok-Code-Fast 1 xAI 43.6 44.3 45.5 45.1 – – $0.53
167 Grok 3 xAI 43.8 42.9 45.3 43.4 44.5 43.2 –
166 Grok-3 mini xAI 43.9 42.1 – 45.1 47.3 – –
165 MiniMax-M2 MiniMax Open 44.0 – 46.7 44.2 – – $0.53
164 Qwen3 235B-A22B Thinking 2507 Alibaba Open 44.3 47.5 30.6 45.8 48.0 53.4 $0.95
163 GPT-4.1 OpenAI 44.3 42.0 45.1 42.3 43.2 44.3 $3.50
162 GPT OSS 120B OpenAI Open 44.4 44.1 42.1 44.7 53.5 42.2 $0.26
161 Trinity Large Thinking Arcee AI Open 44.5 46.8 – 45.1 – – $0.41
160 Qwen3 235B-A22B Alibaba Open 44.5 45.0 – 44.4 39.0 45.0 $0.50
159 GPT-5 Nano OpenAI 44.6 47.9 44.0 46.8 50.2 39.2 $0.14
158 Gemini 2.5 Flash (Apr 2025) Google 44.8 41.5 – 45.2 49.2 46.3 –
157 Qwen3.5 Plus Alibaba 45.0 54.3 30.6 51.4 51.7 49.7 $0.90
156 o3-mini OpenAI 45.2 44.6 – 46.6 49.4 42.0 $1.93
155 Mistral Medium 3.5 Mistral Open 45.3 45.1 – 40.8 52.4 – $3.14
154 Mercury 2.5 Inception 45.4 46.8 51.8 40.8 50.3 35.4 $0.34
153 Qwen3 235B-A22B Instruct 2507 Alibaba Open 45.4 44.8 44.3 44.3 – – $0.31
152 Qwen3-Coder 480B-A35B Instruct Alibaba Open 45.8 47.5 45.9 – – – $0.62
151 Qwen3.5 122B-A10B Alibaba Open 46.0 42.0 – 49.5 – – $0.79
150 DeepSeek-R1 DeepSeek Open 46.0 45.3 43.3 45.9 46.6 48.0 $2.36
149 Gemini 2.5 Flash Preview 05-20 Google 46.2 43.6 – 47.2 48.7 45.3 $0.94
148 o1 OpenAI 46.3 44.9 42.8 48.4 48.5 48.1 $26.25
147 GLM-4.5 Zhipu AI Open 46.4 46.6 – 46.8 – 42.9 $1.00
146 Claude Sonnet 3.7 Anthropic 46.4 46.1 47.1 47.0 45.6 42.8 $6.00
145 Gemini 2.5 Flash-Lite Preview 09-2025 Google 46.4 48.4 – 45.6 – 42.1 $0.18
144 Qwen3.6 35B-A3B Alibaba Open 46.4 44.1 45.1 49.7 49.9 – $0.36
143 DeepSeek-V3.1-Terminus DeepSeek Open 46.5 44.3 – 47.5 – – –
142 Claude Haiku 4.5 Anthropic 46.7 47.8 49.9 47.6 48.3 41.9 $2.00
141 DeepSeek Chat DeepSeek Open 46.8 47.8 – 46.3 45.0 – $0.33
140 Kimi K2 Instruct Moonshot AI Open 46.8 46.6 46.4 44.1 – 42.5 $0.88
139 Mistral Medium 3.5 Mistral 46.9 51.7 49.5 38.4 53.3 38.9 $3.00
138 GLM-4.6 Zhipu AI Open 46.9 48.6 47.8 45.1 45.8 46.5 $1.00