MMODELYST
Leaderboards/MATH Leaderboard
LDR

MATH Leaderboard

MATH

Competition mathematics ranking.

1GPT-5
99.4
2Grok 3 mini Reasoning
99.2
3o3
99.2
4Claude 4 Sonnet
99.1
5Grok 4
99
6o4-mini
98.9
8Qwen3 235B A22B 2507
98.4
11Claude 4 Opus
98.2
12Gemini 2.5 Flash Preview
98.1
13Gemini 2.5 Flash
98.1
15MiniMax M1 80k
98
17GLM-4.5
97.9
18EXAONE 4.0 32B
97.7
19Qwen3 30B A3B 2507
97.6
20Qwen3 30B A3B 2507 Instruct
97.5
21o3-mini
97.3
22MiniMax M1 40k
97.2
23Kimi K2
97.1
24o1
97
25Gemini 2.5 Flash-Lite
96.9
26Solar Pro 2
96.7
27Gemini 2.5 Pro
96.7
28DeepSeek R1 (Jan '25)
96.6
29GLM-4.5-Air
96.5
30Magistral Small 1
96.3
31Qwen3 14B
96.1
32Qwen3 32B
96.1
33Qwen3 30B A3B
95.9
35QwQ 32B
95.7
36Sonar Reasoning Pro
95.7
37R1 1776
95.4
41Claude 3.7 Sonnet
94.7
43o1-mini
94.4
45DeepSeek V3 0324
94.2
48Qwen3 4B
93.3
49DeepSeek R1 0528 Qwen3 8B
93.2
50ERNIE 4.5 300B A47B
93.1
51Qwen3 235B A22B
93
53GPT-4.1 mini
92.5
54o1-preview
92.4
56Sonar Reasoning
92.1
57Gemma 4 E4B
91.8
58Magistral Medium 1
91.7
59GPT-4.1
91.3
60Gemini 2.0 Flash
91.1
61QwQ 32B-Preview
91
62Mistral Medium 3
90.7
63Qwen3 8B
90.4
64LFM2.5-8B-A1B
90.2
65DeepSeek-V3
90.2
66Solar Pro 2 (Preview)
90
67Qwen3 1.7B
89.4
70Reka Flash 3
89.3
71Llama 4 Maverick
88.9
72DeepSeek V3 (Dec '24)
88.7
73Mistral Small 3.2
88.3
74Gemma 3 27B Instruct
88.3
75Gemini 1.5 Pro
87.6
78Grok 3
87
79Gemma 4 E2B
86
80Qwen2.5 Instruct 72B
85.8
82Gemma 3 12B Instruct
85.3
83GPT-4.1 nano
84.8
84Sarvam M
84.7
85Llama 4 Scout
84.4
86Nova Premier
83.9
87Qwen2.5 Max
83.5
88Qwen2.5-72B-Instruct
83.1
89Gemini 1.5 Flash (Sep '24)
82.7
90Sonar
81.7
91phi-4
81
92Qwen2.5 Instruct 32B
80.5
93Qwen2.5 Turbo
80.5
94Ministral 3 3B
80
95GPT-4o (ChatGPT)
79.7
96GPT-4o
79.5
97GPT-4o (May '24)
79.1
98GPT-4o mini
78.9
99Nova Pro
78.6
100Claude 3.5 Sonnet
78.3
101Llama 3.1 Tulu3 405B
77.8
102Grok-2
77.8
103Llama 3.3 Instruct 70B
77.3
104Gemma 3n E4B Instruct
77.1
105Llama-3.3-70B-Instruct
77
106Qwen2.5 Coder Instruct 32B
76.7
107Gemma 3 4B Instruct
76.6
108Nova Lite
76.5
109DeepSeek-V2.5 (Dec '24)
76.3
110GPT-4o (Nov '24)
75.9
111Qwen2.5-7B-Instruct
75.5
112LFM2 2.6B
75.3
113Qwen3 0.6B
75
115Sonar Pro
74.5
116DeepSeek-Coder-V2
74.3
117Grok Beta
73.7
118GPT-4 Turbo
73.7
119Mistral Large 2 (Nov '24)
73.6
121Qwen3.5 4B
73.1
122Claude 3.5 Haiku
72.1
123LFM2.5-1.2B-Instruct
71.7
124Mistral Small 3
71.5
125Pixtral Large
71.4
126Mistral Large 2 (Jul '24)
71.4
127Devstral Medium
70.7
128Mistral Small 3.1
70.7
129Nova Micro
70.3
130Llama 3.1 Instruct 405B
70.3
131Qwen2 Instruct 72B
70.1
132Phi-4-mini-instruct
69.6
133Claude 3.5 Sonnet (June '24)
69.5
134Phi-4 Multimodal Instruct
69.3
135Gemma 3n E2B Instruct
69.1
136Gemini 1.5 Flash-8B
68.9
138Devstral Small (May '25)
68.4
139Llama-3.1-70B-Instruct
68
140Mistral Saba
67.7
141Gemini 1.5 Pro (May '24)
67.3
142Granite 3.3 8B
66.5
143Qwen2.5 Coder Instruct 7B
66
144Llama 3.1 Instruct 70B
64.9
145Claude 3 Opus
64.1
146Devstral Small (Jul '25)
63.5
148Granite 4.0 Micro
62.7
149Jamba 1.5 Large
60.6
150Jamba 1.7 Large
60
152Jamba 1.6 Large
58
153Mistral Small (Sep '24)
56.3
154Mistral Small (Feb '24)
56.2
155Gemini 1.5 Flash (May '24)
55.4
156Mixtral 8x22B Instruct
54.5
157Hermes 3 - Llama-3.1 70B
53.8
158Reka Flash (Sep '24)
52.9
159Mistral Large (Feb '24)
52.7
160Granite 4.0 H 1B
52.2
161Llama 3.1 Instruct 8B
51.9
162Llama-3.1-8B-Instruct
51.9
164gemma-2-27b-it
50
165Llama 3 Instruct 8B
49.9
166Gemma 3 1B Instruct
48.4
167Llama 3 Instruct 70B
48.3
168LFM 40B
48
170Llama 3.2 Instruct 3B
47
171Phi-3 Mini Instruct 3.8B
45.7
172GPT-3.5 Turbo
44.1
173Qwen3.5 2B
43
174Claude 3 Sonnet
41.4
175Mistral Medium
40.5
176Gemini 1.0 Pro
40.3
177Claude 3 Haiku
39.4
178Claude 2.1
37.4
179Jamba 1.5 Mini
35.7
180Solar Mini
33.1
181Llama 2 Chat 13B
32.9
182Llama 2 Chat 70B
32.3
183OpenChat 3.5 (1210)
30.7
184Mixtral 8x7B Instruct
29.9
185Command-R+ (Apr '24)
27.9
186DBRX Instruct
27.9
187Llama 3.2 Instruct 1B
27.7
188Claude Instant
26.4
189Jamba 1.7 Mini
25.8
190Jamba 1.6 Mini
25.7
192Command-R (Mar '24)
16.4
193Granite 4.0 350M
14
194Mistral 7B Instruct
12.1
195Granite 4.0 H 350M
11.6
196Qwen3.5 0.8B
9.3
197Llama 2 Chat 7B
5.9