Intelligence vs. Price by Gemini Endpoint

Rank Model Name Score Organization
1 GPT-5 (high) 68.95 OpenAI
2 GPT-5 (medium) 67.53 OpenAI
3 Grok 4 67.52 xAI
4 o3 67.07 OpenAI
5 O3 Pro 67.07 OpenAI
6 O3 Mini 67.07 OpenAI
7 o4-mini (high) 65.05 OpenAI
8 Gemini 2.5 Pro 64.63 Google
9 Gemini 2 5 Pro 05 06 64.63 Google
10 Gemini 2 5 Pro 03 25 64.63 Google
11 Gpt 5 Mini 63.70 OpenAI
12 Qwen3 235B 2507 (Reasoning) 63.59 Alibaba
13 GPT-5 (low) 63.43 OpenAI
14 gpt-oss-120B (high) 61.34 OpenAI
15 Claude 4.1 Opus Thinking 61.00 Anthropic
16 Claude 4 Sonnet Thinking 58.83 Anthropic
17 DeepSeek R1 0528 58.58 Unknown
18 Gemini 2.5 Flash (Reasoning) 58.43 Google
19 Gemini 2 5 Flash Reasoning 04 2025 58.43 Google
20 Grok 3 mini Reasoning (high) 58.01 xAI
21 Gemini 2.5 Pro (May' 25) 57.98 Google
22 GLM-4.5 56.08 Zhipu AI
23 Glm 4 5 Air 56.08 Zhipu AI
24 O3 Mini High 55.46 OpenAI
25 Claude 4 Opus Thinking 55.34 Anthropic
26 Gpt 5 Nano 53.78 OpenAI
27 MiniMax M1 80k 53.15 Unknown
28 Llama Nemotron Super 49B v1.5 (Reasoning) 52.40 Meta
29 O1 51.68 Unknown
30 MiniMax M1 40k 51.11 Unknown
31 Sonar Reasoning Pro 50.74 Unknown
32 EXAONE 4.0 32B (Reasoning) 50.70 Unknown
33 o1-preview 49.30 Unknown
34 gpt-oss-20B (high) 49.01 OpenAI
35 Claude 4 1 Opus 49.00 Anthropic
36 Kimi K2 48.56 Unknown
37 QwQ-32B 47.68 Unknown
38 Gemini 2 5 Flash 47.26 Google
39 Gemini 2.5 Flash-Lite (Reasoning) 47.25 Google
40 Claude 3 7 Sonnet Thinking 46.98 Anthropic
41 GPT-4.1 46.77 OpenAI
42 Gpt 4 1 Nano 46.77 OpenAI
43 Gpt 4 1 Mini 46.77 OpenAI
44 Claude 4 Opus 46.58 Anthropic
45 Llama Nemotron Ultra Reasoning 46.42 Meta
46 Claude 4 Sonnet 45.72 Anthropic
47 o1-pro 45.63 Unknown
48 Qwen3 Coder 480B 45.19 Alibaba
49 Qwen3 Coder 480b A35b Instruct 45.19 Alibaba
50 Qwen3 32B (Reasoning) 44.28 Alibaba
51 DeepSeek V3 0324 (Mar '25) 43.99 Unknown
52 GPT-5 (minimal) 43.76 OpenAI
53 Solar Pro 2 (Reasoning) 43.30 Unknown
54 O1 Mini 43.25 Unknown
55 Nvidia Nemotron Nano 9b V2 Reasoning 43.22 Unknown
56 GPT-4.5 (Preview) 42.41 OpenAI
57 Llama 4 Maverick 41.73 Meta
58 Gemini 2.0 Flash Thinking exp. (Jan '25) 41.70 Google
59 Deepseek R1 Distill Qwen 32b 41.25 Alibaba
60 Llama 3.3 Nemotron Super 49B Reasoning 40.47 Meta
61 Grok 3 39.92 xAI
62 GPT-4o (March 2025) 39.52 OpenAI
63 Mistral Medium 3 38.59 Unknown
64 Gemini 2 0 Pro Experimental 02 05 38.43 Google
65 DeepSeek R1 Distill Qwen 14B 38.22 Alibaba
66 Sonar Reasoning 38.04 Unknown
67 Gemini 2.5 Flash (April '25) 37.97 Google
68 Mistral Medium 3 1 37.97 Unknown
69 Gemini 2.0 Flash 37.81 Google
70 Magistral Medium 37.57 Unknown
71 Deepseek R1 Distill Llama 70b 37.42 Meta
72 Claude 3.7 Sonnet 37.33 Anthropic
73 EXAONE 4.0 32B 37.22 Unknown
74 Qwen3 4B (Reasoning) 36.40 Alibaba
75 Reka Flash 3 36.26 Unknown
76 Magistral Small 35.95 Unknown
77 Gemini 2 0 Flash Experimental 35.51 Google
78 Gemini 2.5 Flash-Lite 34.92 Google
79 Nova Premier 34.76 Unknown
80 DeepSeek V3 (Dec '24) 34.65 Unknown
81 Qwen2.5 Max 34.33 Alibaba
82 Gemini 1.5 Pro (Sep) 33.62 Google
83 Solar Pro 2 Preview 33.62 Unknown
84 Claude 3.5 Sonnet (Oct) 33.46 Anthropic
85 Qwen3 Coder 30B 33.45 Alibaba
86 Qwen3 Coder 30b A3b Instruct 33.45 Alibaba
87 Qwen3 235B 33.33 Alibaba
88 Qwen3 235b A22b Instruct 33.33 Alibaba
89 Solar Pro 2 33.23 Unknown
90 Llama 4 Scout 33.06 Meta
91 Sonar 32.36 Unknown
92 Mistral Small 3 2 31.82 Unknown
93 Sonar Pro 31.67 Unknown
94 Command A 31.59 Unknown
95 Devstral Medium 31.26 Unknown
96 Llama 3.3 70B 31.21 Meta
97 Qwen3 30b A3b Instruct 29.91 Alibaba
98 Qwen3 14B 29.84 Alibaba
99 Qwen3 14b Instruct 29.84 Alibaba
100 Qwen3 32B 29.82 Alibaba
101 Qwen3 32b Instruct 29.82 Alibaba
102 Gemini 2 0 Flash Lite Preview 29.70 Google
103 GPT-4o (Aug '24) 29.38 OpenAI
104 Llama 3.1 405B 29.33 Meta
105 Qwen2.5 72B 29.25 Alibaba
106 Qwen2 5 72b Instruct 29.25 Alibaba
107 Minimax Text 01 29.06 Unknown
108 Nova Pro 28.83 Unknown
109 Claude 3.5 Sonnet (June) 28.82 Anthropic
110 Tulu3 405b 28.74 Unknown
111 GPT-4o (ChatGPT) 28.64 OpenAI
112 Grok 2 28.02 xAI
113 Grok 2 1212 28.02 xAI
114 Phi-4 27.95 Unknown
115 Gemini 1.5 Flash (Sep) 27.74 Google
116 Gpt 4 Turbo 27.52 OpenAI
117 Mistral Large 2 (Nov '24) 27.01 Unknown
118 Llama Nemotron Super 49b V1 5 26.94 Meta
119 Qwen3 1.7B (Reasoning) 26.89 Alibaba
120 Mistral Small 3 1 26.37 Unknown
121 Grok Beta 26.25 xAI
122 Pixtral Large 2411 26.12 Unknown
123 Qwen2.5 Instruct 32B 26.11 Alibaba
124 Qwen3 8B 25.39 Alibaba
125 Qwen3 8b Instruct 25.39 Alibaba
126 Gemma 3 27b 25.22 Unknown
127 Qwen2 5 Coder 32b Instruct 24.99 Alibaba
128 GPT-4 24.64 OpenAI
129 Nova Lite 24.54 Unknown
130 Gpt 4o Mini 24.31 OpenAI
131 Llama 3.1 70B 23.99 Meta
132 Gemma 3 12b 23.99 Unknown
133 Mistral Small 3 23.89 Unknown
134 DeepSeek-V2.5 (Dec '24) 23.88 Unknown
135 Qwen3 4b Instruct 23.82 Alibaba
136 Claude 3 Opus 23.69 Anthropic
137 Claude 3.5 Haiku 23.33 Anthropic
138 Gemini 2.0 Flash Thinking exp. (Dec '24) 23.31 Google
139 DeepSeek-V2.5 23.28 Unknown
140 Deepseek V2 5 Sep 2024 23.28 Unknown
141 Devstral Small (May '25) 22.67 Unknown
142 Mistral Saba 22.65 Unknown
143 Deepseek R1 Distill Llama 8b 22.55 Meta
144 Reka Core 22.42 Unknown
145 Gemini 1.5 Pro (May) 22.21 Google
146 Gemini 1 5 Pro May 2024 22.21 Google
147 R1 1776 22.19 Unknown
148 Qwen2.5 Turbo 22.14 Alibaba
149 Reka Flash 22.11 Unknown
150 Solar Mini 21.90 Unknown
151 Reka Edge 21.49 Unknown
152 Grok 1 21.19 xAI
153 Qwen2 72b Instruct 21.09 Alibaba
154 Devstral Small 20.54 Unknown
155 Nova Micro 20.24 Unknown
156 Gemma 2 27B 20.11 Unknown
157 Gemini 1.5 Flash-8B 19.24 Google
158 Llama 3.1 8B 19.01 Meta
159 Gemma 3n E4B 18.48 Unknown
160 Deephermes 3 Mistral 24b Preview 18.37 Unknown
161 Jamba 1.7 Large 17.91 Unknown
162 Jamba 1.5 Large 17.66 Unknown
163 Granite 3.3 8B 17.63 Unknown
164 Granite 3 3 8b Instruct 17.63 Unknown
165 Hermes 3 Llama 3 1 70b 17.48 Meta
166 Deepseek Coder V2 17.33 Unknown
167 Jamba 1.6 Large 17.13 Unknown
168 Gemini 1.5 Flash (May) 16.78 Google
169 Gemini 1 5 Flash May 2024 16.78 Google
170 Yi-Large 16.17 Unknown
171 Claude 3 Sonnet 16.05 Anthropic
172 Mistral Small (Sep '24) 15.69 Unknown
173 Gemini 1 0 Ultra 15.57 Google
174 Phi-4 Multimodal 15.15 Unknown
175 Qwen2 5 Coder 7b Instruct 14.92 Alibaba
176 Jamba Instruct 14.51 Unknown
177 Mixtral 8x22B 14.37 Unknown
178 Phi 4 Mini 14.16 Unknown
179 Llama 2 Chat 7B 13.94 Meta
180 Gemma 3 4b 13.52 Unknown
181 Claude 2.1 12.22 Anthropic
182 Claude 3 Haiku 12.11 Anthropic
183 Qwen3 0.6B (Reasoning) 11.28 Alibaba
184 Claude 2.0 11.07 Anthropic
185 DeepSeek-V2 11.07 Unknown
186 Mistral Medium 10.86 Unknown
187 Gemma 3n E2B 10.44 Unknown
188 Ministral 8b 10.37 Unknown
189 Gemma 2 9B 10.23 Unknown
190 Phi-3 Mini 10.13 Unknown
191 Qwen Chat 72b 10.02 Alibaba
192 Arctic Instruct 10.02 Unknown
193 Lfm 40b 9.74 Unknown
194 Command R Plus 9.49 Unknown
195 Llama 3 8B 9.47 Meta
196 PALM-2 8.98 Unknown
197 Gemini 1 0 Pro 8.55 Google
198 DeepSeek Coder V2 Lite 8.45 Unknown
199 Aya Expanse 32b 7.99 Unknown
200 Llama 2 Chat 70b 7.93 Meta
201 Llama 2 Chat 13B 7.87 Meta
202 OpenChat 3.5 7.69 Unknown
203 Dbrx 7.67 Unknown
204 Ministral 3b 7.54 Unknown
205 Mistral Nemo 7.52 Unknown
206 Llama 3.2 3B 7.43 Meta
207 Deepseek R1 Distill Qwen 1 5b 7.07 Alibaba
208 Jamba 1.5 Mini 6.27 Unknown
209 Jamba 1 7 Mini 5.75 Unknown
210 Jamba 1.6 Mini 5.49 Unknown
211 Mixtral 8x7b Instruct 4.78 Unknown
212 Qwen3 0.6B 4.49 Alibaba
213 DeepHermes 3 - Llama-3.1 8B 3.99 Meta
214 Deephermes 3 Llama 3 1 8b Preview 3.99 Meta
215 Aya Expanse 8B 3.79 Unknown
216 Command-R+ 2.53 Unknown
217 Claude Instant 1.67 Anthropic
218 Qwen Chat 14b 1.67 Alibaba
219 Codestral-Mamba 1.56 Unknown
220 Gemma 3 1b 1.06 Unknown
221 Llama 3.2 1B 1.00 Meta
222 Mistral 7b Instruct 1.00 Unknown
223 Llama 65b 1.00 Meta
224 GPT-4o Realtime (Dec '24) N/A OpenAI
225 Grok 3 mini Reasoning (low) N/A xAI
226 Gpt 3 5 Turbo 0613 N/A OpenAI