Math Index by Gemini Endpoint

Rank Model Name Score Organization
1 GPT-5 (high) 97.53 OpenAI
2 Grok 4 96.67 xAI
3 o4-mini (high) 96.43 OpenAI
4 Grok 3 mini Reasoning (high) 96.27 xAI
5 Qwen3 235B 2507 (Reasoning) 96.20 Alibaba
6 GPT-5 (medium) 95.40 OpenAI
7 o3 94.77 OpenAI
8 O3 Pro 94.77 OpenAI
9 DeepSeek R1 0528 93.80 Unknown
10 Gemini 2.5 Pro 92.70 Google
11 Gemini 2 5 Pro 05 06 92.70 Google
12 Gemini 2 5 Pro 03 25 92.70 Google
13 GLM-4.5 92.60 Zhipu AI
14 O3 Mini High 92.23 OpenAI
15 Llama Nemotron Super 49B v1.5 (Reasoning) 92.17 Meta
16 Gemini 2.5 Pro (May' 25) 91.47 Google
17 MiniMax M1 80k 91.33 Unknown
18 EXAONE 4.0 32B (Reasoning) 91.00 Unknown
19 GPT-5 (low) 90.87 OpenAI
20 Gemini 2.5 Flash (Reasoning) 90.23 Google
21 Gemini 2 5 Flash Reasoning 04 2025 90.23 Google
22 MiniMax M1 40k 89.27 Unknown
23 Qwen3 32B (Reasoning) 88.37 Alibaba
24 Claude 4 Sonnet Thinking 88.20 Anthropic
25 Sonar Reasoning Pro 87.37 Unknown
26 O3 Mini 87.17 OpenAI
27 Claude 4 Opus Thinking 86.93 Anthropic
28 QwQ-32B 86.87 Unknown
29 Llama Nemotron Ultra Reasoning 84.93 Meta
30 O1 84.67 Unknown
31 Sonar Reasoning 84.57 Unknown
32 Magistral Small 83.80 Unknown
33 Gemini 2.5 Flash-Lite (Reasoning) 83.60 Google
34 Kimi K2 83.23 Unknown
35 Solar Pro 2 (Reasoning) 82.83 Unknown
36 Glm 4 5 Air 81.93 Zhipu AI
37 Deepseek R1 Distill Qwen 32b 81.37 Alibaba
38 Magistral Medium 80.87 Unknown
39 DeepSeek R1 Distill Qwen 14B 80.77 Alibaba
40 Deepseek R1 Distill Llama 70b 80.23 Meta
41 Qwen3 4B (Reasoning) 79.50 Alibaba
42 O1 Mini 77.37 Unknown
43 Llama 3.3 Nemotron Super 49B Reasoning 77.10 Meta
44 Claude 4 Opus 75.20 Anthropic
45 DeepSeek V3 0324 (Mar '25) 73.10 Unknown
46 Gemini 2.0 Flash Thinking exp. (Jan '25) 72.20 Google
47 Claude 3 7 Sonnet Thinking 71.67 Anthropic
48 Gemini 2 5 Flash 71.60 Google
49 Gemini 2.5 Flash-Lite 71.30 Google
50 Qwen3 Coder 480B 70.93 Alibaba
51 Qwen3 Coder 480b A35b Instruct 70.93 Alibaba
52 EXAONE 4.0 32B 70.47 Unknown
53 Qwen3 1.7B (Reasoning) 70.20 Alibaba
54 Reka Flash 3 70.13 Unknown
55 Gemini 2.5 Flash (April '25) 67.97 Google
56 GPT-4.1 67.47 OpenAI
57 Gpt 4 1 Mini 67.47 OpenAI
58 Mistral Medium 3 67.33 Unknown
59 Claude 4 Sonnet 67.03 Anthropic
60 Sonar 65.17 Unknown
61 Solar Pro 2 64.77 Unknown
62 Gemini 2 0 Pro Experimental 02 05 64.13 Google
63 Llama 4 Maverick 63.93 Meta
64 Gemini 2.0 Flash 63.00 Google
65 Qwen3 235B 61.43 Alibaba
66 Qwen3 235b A22b Instruct 61.43 Alibaba
67 GPT-5 (minimal) 61.40 OpenAI
68 GPT-4o (March 2025) 60.97 OpenAI
69 Gemini 2 0 Flash Experimental 60.53 Google
70 Mistral Small 3 2 60.30 Unknown
71 Grok 3 60.00 xAI
72 Qwen3 Coder 30B 59.50 Alibaba
73 Qwen3 Coder 30b A3b Instruct 59.50 Alibaba
74 Deepseek R1 Distill Llama 8b 59.30 Meta
75 Gemini 2 0 Flash Lite Preview 58.83 Google
76 Qwen3 32B 58.60 Alibaba
77 Qwen3 32b Instruct 58.60 Alibaba
78 Solar Pro 2 Preview 58.37 Unknown
79 Qwen3 14B 57.57 Alibaba
80 Qwen3 14b Instruct 57.57 Alibaba
81 DeepSeek V3 (Dec '24) 57.00 Unknown
82 Gemma 3 27b 56.80 Unknown
83 Llama 4 Scout 56.37 Meta
84 Qwen3 30b A3b Instruct 56.13 Alibaba
85 Gemini 1.5 Pro (Sep) 55.30 Google
86 Gpt 4 1 Nano 54.23 OpenAI
87 Claude 3.7 Sonnet 53.67 Anthropic
88 Gemma 3 12b 53.67 Unknown
89 Llama 3.3 70B 53.63 Meta
90 Qwen3 8B 53.57 Alibaba
91 Qwen3 8b Instruct 53.57 Alibaba
92 Qwen2.5 Max 53.40 Alibaba
93 Qwen3 4b Instruct 52.80 Alibaba
94 Sonar Pro 51.73 Unknown
95 Qwen2.5 72B 50.90 Alibaba
96 Qwen2 5 72b Instruct 50.90 Alibaba
97 Nova Premier 50.47 Unknown
98 Gemini 1.5 Flash (Sep) 50.37 Google
99 Phi-4 47.67 Unknown
100 Claude 3.5 Sonnet (Oct) 46.40 Anthropic
101 Qwen2.5 Turbo 46.27 Alibaba
102 Llama 3.1 405B 45.83 Meta
103 Qwen2.5 Instruct 32B 45.77 Alibaba
104 Command A 45.77 Unknown
105 GPT-4o (Aug '24) 45.57 OpenAI
106 Grok 2 45.57 xAI
107 Grok 2 1212 45.57 xAI
108 Tulu3 405b 45.57 Unknown
109 Gemma 3n E4B 45.37 Unknown
110 Llama Nemotron Super 49b V1 5 45.33 Meta
111 Gpt 4o Mini 45.27 OpenAI
112 GPT-4o (ChatGPT) 45.03 OpenAI
113 Nova Pro 44.63 Unknown
114 Qwen2 5 Coder 32b Instruct 44.33 Alibaba
115 Gpt 4 Turbo 44.33 OpenAI
116 Minimax Text 01 44.17 Unknown
117 Nova Lite 43.57 Unknown
118 Deepseek R1 Distill Qwen 1 5b 43.20 Alibaba
119 Qwen3 0.6B (Reasoning) 42.50 Alibaba
120 Qwen2 72b Instruct 42.40 Alibaba
121 Mistral Large 2 (Nov '24) 42.30 Unknown
122 Grok Beta 42.00 xAI
123 Gemma 2 27B 41.87 Unknown
124 Gemma 3 4b 41.47 Unknown
125 Llama 3.1 70B 41.13 Meta
126 Mistral Saba 40.33 Unknown
127 Mistral Small 3 1 40.00 Unknown
128 Mistral Small 3 39.77 Unknown
129 Claude 3.5 Sonnet (June) 39.60 Anthropic
130 Phi-4 Multimodal 39.30 Unknown
131 Pixtral Large 2411 39.20 Unknown
132 Nova Micro 39.17 Unknown
133 Gemma 3n E2B 39.07 Unknown
134 Devstral Medium 38.70 Unknown
135 Claude 3.5 Haiku 37.70 Anthropic
136 Gemini 1.5 Pro (May) 37.67 Google
137 Gemini 1 5 Pro May 2024 37.67 Google
138 Devstral Small (May '25) 37.53 Unknown
139 Phi 4 Mini 36.30 Unknown
140 Gemini 1.5 Flash-8B 36.13 Google
141 Qwen2 5 Coder 7b Instruct 35.67 Alibaba
142 Granite 3.3 8B 35.57 Unknown
143 Granite 3 3 8b Instruct 35.57 Unknown
144 Claude 3 Opus 33.70 Anthropic
145 Jamba 1.7 Large 32.83 Unknown
146 Jamba 1.5 Large 32.63 Unknown
147 Gemini 1.5 Flash (May) 32.37 Google
148 Gemini 1 5 Flash May 2024 32.37 Google
149 Deephermes 3 Mistral 24b Preview 32.07 Unknown
150 Devstral Small 31.90 Unknown
151 Yi-Large 31.43 Unknown
152 Jamba 1.6 Large 31.33 Unknown
153 Mistral Small (Sep '24) 31.30 Unknown
154 Ministral 8b 30.37 Unknown
155 Llama 3.1 8B 29.80 Meta
156 Hermes 3 Llama 3 1 70b 28.07 Meta
157 Llama 3.2 3B 27.77 Meta
158 Mixtral 8x22B 27.23 Unknown
159 Qwen3 0.6B 26.87 Alibaba
160 Ministral 3b 26.83 Unknown
161 Gemma 2 9B 25.87 Unknown
162 Lfm 40b 25.17 Unknown
163 Llama 3 8B 24.97 Meta
164 Phi-3 Mini 24.83 Unknown
165 Gemma 3 1b 24.20 Unknown
166 Claude 3 Sonnet 23.03 Anthropic
167 Aya Expanse 32b 22.43 Unknown
168 Mistral Medium 22.07 Unknown
169 Gemini 1 0 Pro 20.47 Google
170 Claude 2.1 20.37 Anthropic
171 Claude 3 Haiku 20.20 Anthropic
172 Command R Plus 20.10 Unknown
173 Mistral Nemo 19.90 Unknown
174 Jamba 1.5 Mini 18.33 Unknown
175 Llama 2 Chat 13B 17.27 Meta
176 Llama 2 Chat 70b 16.13 Meta
177 Aya Expanse 8B 16.03 Unknown
178 Dbrx 15.47 Unknown
179 OpenChat 3.5 15.37 Unknown
180 Mixtral 8x7b Instruct 14.97 Unknown
181 Jamba 1.6 Mini 14.50 Unknown
182 Jamba 1 7 Mini 13.57 Unknown
183 Claude Instant 13.20 Anthropic
184 Codestral-Mamba 12.00 Unknown
185 DeepHermes 3 - Llama-3.1 8B 10.90 Meta
186 Deephermes 3 Llama 3 1 8b Preview 10.90 Meta
187 Command-R+ 7.63 Unknown
188 Llama 3.2 1B 7.00 Meta
189 Mistral 7b Instruct 6.07 Unknown
190 Llama 2 Chat 7B 2.93 Meta