M
MODELYST
AI research terminal
●
live · verified Jul 27
Search
⌘K
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
Frontier
Models
Compare
Leaderboards
Changes
Media
Benchmarks
Papers
Pick
Discover
Ask
Leaderboards
/
MATH Leaderboard
LDR
MATH Leaderboard
MATH
☆ Watch
Competition mathematics ranking.
1
GPT-5
Jul 27, 2026
99.4
2
Grok 3 mini Reasoning
Jul 27, 2026
99.2
3
o3
Jul 27, 2026
99.2
4
Claude 4 Sonnet
Jul 27, 2026
99.1
5
Grok 4
Jul 27, 2026
99
6
o4-mini
Jul 27, 2026
98.9
7
Gemini 2.5 Pro Preview (May' 25)
Jul 27, 2026
98.6
8
Qwen3 235B A22B 2507
Jul 27, 2026
98.4
9
DeepSeek R1 0528 (May '25)
Jul 27, 2026
98.3
10
Llama Nemotron Super 49B v1.5
Jul 27, 2026
98.3
11
Claude 4 Opus
Jul 27, 2026
98.2
12
Gemini 2.5 Flash Preview
Jul 27, 2026
98.1
13
Gemini 2.5 Flash
Jul 27, 2026
98.1
14
Qwen3 235B A22B 2507 Instruct
Jul 27, 2026
98
15
MiniMax M1 80k
Jul 27, 2026
98
16
Gemini 2.5 Pro Preview (Mar' 25)
Jul 27, 2026
98
17
GLM-4.5
Jul 27, 2026
97.9
18
EXAONE 4.0 32B
Jul 27, 2026
97.7
19
Qwen3 30B A3B 2507
Jul 27, 2026
97.6
20
Qwen3 30B A3B 2507 Instruct
Jul 27, 2026
97.5
21
o3-mini
Jul 27, 2026
97.3
22
MiniMax M1 40k
Jul 27, 2026
97.2
23
Kimi K2
Jul 27, 2026
97.1
24
o1
Jul 27, 2026
97
25
Gemini 2.5 Flash-Lite
Jul 27, 2026
96.9
26
Solar Pro 2
Jul 27, 2026
96.7
27
Gemini 2.5 Pro
Jul 27, 2026
96.7
28
DeepSeek R1 (Jan '25)
Jul 27, 2026
96.6
29
GLM-4.5-Air
Jul 27, 2026
96.5
30
Magistral Small 1
Jul 27, 2026
96.3
31
Qwen3 14B
Jul 27, 2026
96.1
32
Qwen3 32B
Jul 27, 2026
96.1
33
Qwen3 30B A3B
Jul 27, 2026
95.9
34
Llama-3_3-Nemotron-Super-49B-v1
Jul 27, 2026
95.9
35
QwQ 32B
Jul 27, 2026
95.7
36
Sonar Reasoning Pro
Jul 27, 2026
95.7
37
R1 1776
Jul 27, 2026
95.4
38
Llama 3.1 Nemotron Ultra 253B v1
Jul 27, 2026
95.2
39
DeepSeek R1 Distill Qwen 14B
Jul 27, 2026
94.9
40
Llama 3.1 Nemotron Nano 4B v1.1
Jul 27, 2026
94.7
41
Claude 3.7 Sonnet
Jul 27, 2026
94.7
42
Gemini 2.0 Flash Thinking Experimental (Jan '25)
Jul 27, 2026
94.4
43
o1-mini
Jul 27, 2026
94.4
44
Qwen3 Coder 480B A35B Instruct
Jul 27, 2026
94.2
45
DeepSeek V3 0324
Jul 27, 2026
94.2
46
DeepSeek R1 Distill Qwen 32B
Jul 27, 2026
94.1
47
DeepSeek R1 Distill Llama 70B
Jul 27, 2026
93.5
48
Qwen3 4B
Jul 27, 2026
93.3
49
DeepSeek R1 0528 Qwen3 8B
Jul 27, 2026
93.2
50
ERNIE 4.5 300B A47B
Jul 27, 2026
93.1
51
Qwen3 235B A22B
Jul 27, 2026
93
52
Gemini 2.0 Flash (Feb '25)
Jul 27, 2026
93
53
GPT-4.1 mini
Jul 27, 2026
92.5
54
o1-preview
Jul 27, 2026
92.4
55
Gemini 2.0 Pro Experimental (Feb '25)
Jul 27, 2026
92.3
56
Sonar Reasoning
Jul 27, 2026
92.1
57
Gemma 4 E4B
Jul 27, 2026
91.8
58
Magistral Medium 1
Jul 27, 2026
91.7
59
GPT-4.1
Jul 27, 2026
91.3
60
Gemini 2.0 Flash
Jul 27, 2026
91.1
61
QwQ 32B-Preview
Jul 27, 2026
91
62
Mistral Medium 3
Jul 27, 2026
90.7
63
Qwen3 8B
Jul 27, 2026
90.4
64
LFM2.5-8B-A1B
Jul 27, 2026
90.2
65
DeepSeek-V3
May 31, 2026
90.2
66
Solar Pro 2 (Preview)
Jul 27, 2026
90
67
Qwen3 1.7B
Jul 27, 2026
89.4
68
Qwen3 Coder 30B A3B Instruct
Jul 27, 2026
89.3
69
GPT-4o (March 2025, chatgpt-4o-latest)
Jul 27, 2026
89.3
70
Reka Flash 3
Jul 27, 2026
89.3
71
Llama 4 Maverick
Jul 27, 2026
88.9
72
DeepSeek V3 (Dec '24)
Jul 27, 2026
88.7
73
Mistral Small 3.2
Jul 27, 2026
88.3
74
Gemma 3 27B Instruct
Jul 27, 2026
88.3
75
Gemini 1.5 Pro
Jul 27, 2026
87.6
76
Gemini 2.0 Flash-Lite (Feb '25)
Jul 27, 2026
87.3
77
Gemini 2.0 Flash-Lite (Preview)
Jul 27, 2026
87.3
78
Grok 3
Jul 27, 2026
87
79
Gemma 4 E2B
Jul 27, 2026
86
80
Qwen2.5 Instruct 72B
Jul 27, 2026
85.8
81
DeepSeek R1 Distill Llama 8B
Jul 27, 2026
85.3
82
Gemma 3 12B Instruct
Jul 27, 2026
85.3
83
GPT-4.1 nano
Jul 27, 2026
84.8
84
Sarvam M
Jul 27, 2026
84.7
85
Llama 4 Scout
Jul 27, 2026
84.4
86
Nova Premier
Jul 27, 2026
83.9
87
Qwen2.5 Max
Jul 27, 2026
83.5
88
Qwen2.5-72B-Instruct
May 31, 2026
83.1
89
Gemini 1.5 Flash (Sep '24)
Jul 27, 2026
82.7
90
Sonar
Jul 27, 2026
81.7
91
phi-4
Jul 27, 2026
81
92
Qwen2.5 Instruct 32B
Jul 27, 2026
80.5
93
Qwen2.5 Turbo
Jul 27, 2026
80.5
94
Ministral 3 3B
Jul 27, 2026
80
95
GPT-4o (ChatGPT)
Jul 27, 2026
79.7
96
GPT-4o
Jul 27, 2026
79.5
97
GPT-4o (May '24)
Jul 27, 2026
79.1
98
GPT-4o mini
Jul 27, 2026
78.9
99
Nova Pro
Jul 27, 2026
78.6
100
Claude 3.5 Sonnet
Oct 1, 2024
78.3
101
Llama 3.1 Tulu3 405B
Jul 27, 2026
77.8
102
Grok-2
Jul 27, 2026
77.8
103
Llama 3.3 Instruct 70B
Jul 27, 2026
77.3
104
Gemma 3n E4B Instruct
Jul 27, 2026
77.1
105
Llama-3.3-70B-Instruct
May 31, 2026
77
106
Qwen2.5 Coder Instruct 32B
Jul 27, 2026
76.7
107
Gemma 3 4B Instruct
Jul 27, 2026
76.6
108
Nova Lite
Jul 27, 2026
76.5
109
DeepSeek-V2.5 (Dec '24)
Jul 27, 2026
76.3
110
GPT-4o (Nov '24)
Jul 27, 2026
75.9
111
Qwen2.5-7B-Instruct
May 31, 2026
75.5
112
LFM2 2.6B
Jul 27, 2026
75.3
113
Qwen3 0.6B
Jul 27, 2026
75
114
Gemma 3n E4B Instruct Preview (May '25)
Jul 27, 2026
74.9
115
Sonar Pro
Jul 27, 2026
74.5
116
DeepSeek-Coder-V2
Jul 27, 2026
74.3
117
Grok Beta
Jul 27, 2026
73.7
118
GPT-4 Turbo
Jul 27, 2026
73.7
119
Mistral Large 2 (Nov '24)
Jul 27, 2026
73.6
120
Llama 3.1 Nemotron Instruct 70B
Jul 27, 2026
73.3
121
Qwen3.5 4B
Jul 27, 2026
73.1
122
Claude 3.5 Haiku
Jul 27, 2026
72.1
123
LFM2.5-1.2B-Instruct
Jul 27, 2026
71.7
124
Mistral Small 3
Jul 27, 2026
71.5
125
Pixtral Large
Jul 27, 2026
71.4
126
Mistral Large 2 (Jul '24)
Jul 27, 2026
71.4
127
Devstral Medium
Jul 27, 2026
70.7
128
Mistral Small 3.1
Jul 27, 2026
70.7
129
Nova Micro
Jul 27, 2026
70.3
130
Llama 3.1 Instruct 405B
Jul 27, 2026
70.3
131
Qwen2 Instruct 72B
Jul 27, 2026
70.1
132
Phi-4-mini-instruct
Jul 27, 2026
69.6
133
Claude 3.5 Sonnet (June '24)
Jul 27, 2026
69.5
134
Phi-4 Multimodal Instruct
Jul 27, 2026
69.3
135
Gemma 3n E2B Instruct
Jul 27, 2026
69.1
136
Gemini 1.5 Flash-8B
Jul 27, 2026
68.9
137
DeepSeek R1 Distill Qwen 1.5B
Jul 27, 2026
68.7
138
Devstral Small (May '25)
Jul 27, 2026
68.4
139
Llama-3.1-70B-Instruct
May 31, 2026
68
140
Mistral Saba
Jul 27, 2026
67.7
141
Gemini 1.5 Pro (May '24)
Jul 27, 2026
67.3
142
Granite 3.3 8B
Jul 27, 2026
66.5
143
Qwen2.5 Coder Instruct 7B
Jul 27, 2026
66
144
Llama 3.1 Instruct 70B
Jul 27, 2026
64.9
145
Claude 3 Opus
Jul 27, 2026
64.1
146
Devstral Small (Jul '25)
Jul 27, 2026
63.5
147
Llama 3.2 Instruct 90B (Vision)
Jul 27, 2026
62.9
148
Granite 4.0 Micro
Jul 27, 2026
62.7
149
Jamba 1.5 Large
Jul 27, 2026
60.6
150
Jamba 1.7 Large
Jul 27, 2026
60
151
DeepHermes 3 - Mistral 24B Preview
Jul 27, 2026
59.5
152
Jamba 1.6 Large
Jul 27, 2026
58
153
Mistral Small (Sep '24)
Jul 27, 2026
56.3
154
Mistral Small (Feb '24)
Jul 27, 2026
56.2
155
Gemini 1.5 Flash (May '24)
Jul 27, 2026
55.4
156
Mixtral 8x22B Instruct
Jul 27, 2026
54.5
157
Hermes 3 - Llama-3.1 70B
Jul 27, 2026
53.8
158
Reka Flash (Sep '24)
Jul 27, 2026
52.9
159
Mistral Large (Feb '24)
Jul 27, 2026
52.7
160
Granite 4.0 H 1B
Jul 27, 2026
52.2
161
Llama 3.1 Instruct 8B
Jul 27, 2026
51.9
162
Llama-3.1-8B-Instruct
May 31, 2026
51.9
163
Llama 3.2 Instruct 11B (Vision)
Jul 27, 2026
51.6
164
gemma-2-27b-it
May 31, 2026
50
165
Llama 3 Instruct 8B
Jul 27, 2026
49.9
166
Gemma 3 1B Instruct
Jul 27, 2026
48.4
167
Llama 3 Instruct 70B
Jul 27, 2026
48.3
168
LFM 40B
Jul 27, 2026
48
169
Gemini 2.0 Flash Thinking Experimental (Dec '24)
Jul 27, 2026
48
170
Llama 3.2 Instruct 3B
Jul 27, 2026
47
171
Phi-3 Mini Instruct 3.8B
Jul 27, 2026
45.7
172
GPT-3.5 Turbo
Jul 27, 2026
44.1
173
Qwen3.5 2B
Jul 27, 2026
43
174
Claude 3 Sonnet
Jul 27, 2026
41.4
175
Mistral Medium
Jul 27, 2026
40.5
176
Gemini 1.0 Pro
Jul 27, 2026
40.3
177
Claude 3 Haiku
Jul 27, 2026
39.4
178
Claude 2.1
Jul 27, 2026
37.4
179
Jamba 1.5 Mini
Jul 27, 2026
35.7
180
Solar Mini
Jul 27, 2026
33.1
181
Llama 2 Chat 13B
Jul 27, 2026
32.9
182
Llama 2 Chat 70B
Jul 27, 2026
32.3
183
OpenChat 3.5 (1210)
Jul 27, 2026
30.7
184
Mixtral 8x7B Instruct
Jul 27, 2026
29.9
185
Command-R+ (Apr '24)
Jul 27, 2026
27.9
186
DBRX Instruct
Jul 27, 2026
27.9
187
Llama 3.2 Instruct 1B
Jul 27, 2026
27.7
188
Claude Instant
Jul 27, 2026
26.4
189
Jamba 1.7 Mini
Jul 27, 2026
25.8
190
Jamba 1.6 Mini
Jul 27, 2026
25.7
191
DeepHermes 3 - Llama-3.1 8B Preview
Jul 27, 2026
21.8
192
Command-R (Mar '24)
Jul 27, 2026
16.4
193
Granite 4.0 350M
Jul 27, 2026
14
194
Mistral 7B Instruct
Jul 27, 2026
12.1
195
Granite 4.0 H 350M
Jul 27, 2026
11.6
196
Qwen3.5 0.8B
Jul 27, 2026
9.3
197
Llama 2 Chat 7B
Jul 27, 2026
5.9