All Models

Benchmark Rankings

Math Index

Models ranked by Artificial Analysis Math Index — measuring mathematical reasoning and problem-solving performance.

283 models ranked · Source: Artificial Analysis

#1
OpenAI/GPT-5.2 2 providers
99 #2
GPT-5.2 33 providers
99 #3
GPT-5.2 (OpenAI) 1 provider
99 #4
GPT-5.2 (Azure) 1 provider
99 #5
GPT-5-Codex 12 providers
98.7 #6
DeepSeek-V3.2-Speciale 2 providers
96.7 #7
Gemini 3 Pro Preview 8 providers
95.7 #8
GPT-5.1 Codex 18 providers
95.7 #9
GPT-5.1 Codex (Azure) 1 provider
95.7 #10
Gemini 3 Pro 2 providers
95.7 #11
Z-Ai/GLM 4.7 1 provider
95 #12
GLM-4.7 38 providers
95 #13
GLM 4.7 TEE 1 provider
95 #14
GLM-4.7 (NovitaAI) 1 provider
95 #15
GLM-4.7 (Z AI) 1 provider
95 #16
GLM-4.7 (ByteDance) 1 provider
95 #17
GLM-4.7 (Together AI) 1 provider
95 #18
GLM-4.7 (Vertex AI (OpenAI-compatible)) 1 provider
95 #19
GLM-4.7 (Cerebras) 1 provider
95 #20
GLM-4.7 (EmberCloud) 1 provider
95 #21
Kimi K2 Thinking 21 providers
94.7 #22
Moonshot Kimi K2 Thinking 1 provider
94.7 #23
Kimi K2 Thinking (Vertex AI (OpenAI-compatible)) 1 provider
94.7 #24
KAT-Coder-Pro V1 1 provider
94.7 #25
OpenAI/GPT-5 3 providers
94.3 #26
GPT-5 28 providers
94.3 #27
GPT-5 (OpenAI) 1 provider
94.3 #28
GPT-5 (Azure) 1 provider
94.3 #29
GPT-5.1 28 providers
94 #30
GPT-5.1 (OpenAI) 1 provider
94 #31
GPT-5.1 (Azure) 1 provider
94 #32
OpenAI GPT-5.1 1 provider
94 #33
gpt-oss-120b 69 providers
93.4 #34
GPT-OSS 120B TEE 1 provider
93.4 #35
GPT OSS 120B (ByteDance) 1 provider
93.4 #36
GPT OSS 120B (Together AI) 1 provider
93.4 #37
GPT OSS 120B (Nebius AI) 1 provider
93.4 #38
GPT OSS 120B (SCX.ai (Turbo)) 1 provider
93.4 #39
GPT OSS 120B (Azure) 1 provider
93.4 #40
GPT OSS 120B (Runware) 1 provider
93.4 #41
GPT OSS 120B (Cerebras) 1 provider
93.4 #42
GPT OSS 120B (Groq) 1 provider
93.4 #43
OpenAI GPT OSS 120B 6 providers
93.4 #44
OpenAI GPT 120B 1 provider
93.4 #45
Grok 4 (xAI) 1 provider
92.7 #46
Grok 4 5 providers
92.7 #47
xAI Grok 4 1 provider
92.7 #48
GPT-5.1 Codex mini 17 providers
91.7 #49
GPT-5.1 Codex mini (Azure) 1 provider
91.7 #50
GPT-5 Mini 31 providers
90.7 #51
OpenAI o4-mini 2 providers
90.7 #52
o4-mini 17 providers
90.7 #53
GPT-5 Mini (OpenAI) 1 provider
90.7 #54
o4 Mini (OpenAI) 1 provider
90.7 #55
GPT-5 Mini (Azure) 1 provider
90.7 #56
o4 Mini (Azure) 1 provider
90.7 #57
OpenAI GPT-5 Mini 2 providers
90.7 #58
X-Ai/Grok-4-Fast-Reasoning 1 provider
89.7 #59
grok-4-fast-reasoning 4 providers
89.7 #60
gpt-oss-20b 46 providers
89.3 #61
X-Ai/Grok 4.1 Fast Reasoning 1 provider
89.3 #62
GPT-OSS 20B TEE 1 provider
89.3 #63
grok-4-1-fast-reasoning 8 providers
89.3 #64
GPT OSS 20B (Together AI) 1 provider
89.3 #65
Grok 4.1 Fast Reasoning (Azure AI Foundry) 1 provider
89.3 #66
GPT OSS 20B (Groq) 1 provider
89.3 #67
OpenAI GPT-oss-20b 3 providers
89.3 #68
Ring-1T 2 providers
89.3 #69
xAI Grok 4.1 Fast Reasoning 1 provider
89.3 #70
OpenAI o3 3 providers
88.3 #71
o3 16 providers
88.3 #72
o3 (OpenAI) 1 provider
88.3 #73
o3 (Azure) 1 provider
88.3 #74
INTELLECT-3 1 provider
88 #75
Gemini 2.5 Pro 29 providers
87.7 #76
Gemini 2.5 Pro (Google Vertex AI) 1 provider
87.7 #77
Gemini 2.5 Pro (Google AI Studio) 1 provider
87.7 #78
Google Gemini 2.5 Pro 1 provider
87.7 #79
Ernie 5.0 Thinking Preview 1 provider
85 #80
ERNIE 5.0 1 provider
85 #81
ByteDance-Seed/Seed-OSS-36B-Instruct 3 providers
84.7 #82
GPT-5 Nano 26 providers
83.7 #83
GPT-5 Nano (OpenAI) 1 provider
83.7 #84
GPT-5 Nano (Azure) 1 provider
83.7 #85
OpenAI GPT-5 Nano 2 providers
83.7 #86
Minimax/Minimax-M2.1 1 provider
82.7 #87
MiniMax M2.1 23 providers
82.7 #88
MiniMax M2.1 (NovitaAI) 1 provider
82.7 #89
MiniMax M2.1 (MiniMax) 1 provider
82.7 #90
Qwen3 Max 20 providers
80.7 #91
GLM 4.5 Air 16 providers
80.7 #92
Qwen3 Max Thinking 3 providers
80.7 #93
Qwen3 Max (NovitaAI) 1 provider
80.7 #94
GLM-4.5 Air (Z AI) 1 provider
80.7 #95
Qwen3 Max (Alibaba Cloud) 1 provider
80.7 #96
GLM-4.5 Air (EmberCloud) 1 provider
80.7 #97
zai-org/GLM-4.5-Air 2 providers
80.7 #98
OpenAI o1-preview 1 provider
79.7 #99
Doubao-Seed-Code 1 provider
79.3 #100
Minimax/Minimax-M2 1 provider
78.3 #101
MiniMax-M2 18 providers
78.3 #102
MiniMax M2 (MiniMax) 1 provider
78.3 #103
DeepSeek-R1 18 providers
76 #104
DeepSeek Reasoner 7 providers
76 #105
deepseek-ai/DeepSeek-R1 2 providers
76 #106
Pro/deepseek-ai/DeepSeek-R1 1 provider
76 #107
Qwen3 Max Preview 3 providers
75 #108
Olmo 3 32B Think 2 providers
73.7 #109
Qwen3 VL 30B A3B Instruct 4 providers
72.3 #110
Qwen3 VL 30B A3B Instruct (DeepInfra) 1 provider
72.3 #111
Qwen3 VL 30B A3B Instruct (NovitaAI) 1 provider
72.3 #112
Qwen/Qwen3-VL-30B-A3B-Instruct 3 providers
72.3 #113
Qwen3 235b A22B Instruct 2507 20 providers
71.7 #114
Qwen 3 235b A22B 2507 1 provider
71.7 #115
Qwen3 235B A22B Instruct 2507 (NovitaAI) 1 provider
71.7 #116
Qwen3 235B A22B Instruct 2507 (Nebius AI) 1 provider
71.7 #117
Qwen3 235B A22B Instruct 2507 (Vertex AI (OpenAI-compatible)) 1 provider
71.7 #118
Qwen3 235B A22B Instruct 2507 (Cerebras) 1 provider
71.7 #119
Qwen 3 235B A22B Instruct 2507 1 provider
71.7 #120
Ling-1T 2 providers
71.3 #121
Qwen3 VL 235B A22B Instruct 13 providers
70.7 #122
Qwen/Qwen3-VL-235B-A22B-Instruct 3 providers
70.7 #123
Qwen3 VL 235B A22B Instruct (DeepInfra) 1 provider
70.7 #124
Qwen3 VL 235B A22B Instruct (NovitaAI) 1 provider
70.7 #125
Qwen3 VL 32B Instruct 2 providers
68.3 #126
Qwen/Qwen3-VL-32B-Instruct 2 providers
68.3 #127
Mimo-V2-Flash 5 providers
67.7 #128
Xiaomi/Mimo-V2-Flash 1 provider
67.7 #129
XiaomiMiMo/MiMo-V2-Flash 2 providers
67.7 #130
Qwen3 Next 80B A3B Instruct 19 providers
66.3 #131
Qwen3 30B A3B 2507 1 provider
66.3 #132
Qwen3 Next 80B A3B Instruct (NovitaAI) 1 provider
66.3 #133
Qwen3 Next 80B A3B Instruct (Vertex AI (OpenAI-compatible)) 1 provider
66.3 #134
Qwen 3 Next 80B Instruct 1 provider
66.3 #135
inclusionAI/Ling-flash-2.0 2 providers
65.3 #136
Deepseek R1 Distill Qwen 32B 4 providers
63 #137
Claude Opus 4.5 (latest) 15 providers
62.7 #138
Claude Opus 4.5 18 providers
62.7 #139
nvidia-nemotron-nano-9b-v2 3 providers
62.3 #140
Nemotron Nano 9B 1 provider
62.3 #141
Nemotron Nano 9B v2 1 provider
62.3 #142
MiniMax M1 7 providers
61 #143
MiniMax M1 80K 1 provider
61 #144
Gemini 2.5 Flash 31 providers
60.3 #145
Gemini 2.5 Flash (Google Vertex AI) 1 provider
60.3 #146
Gemini 2.5 Flash (Google AI Studio) 1 provider
60.3 #147
Google Gemini 2.5 Flash 1 provider
60.3 #148
DeepSeek V3.2 32 providers
59 #149
DeepSeek V3.2 Exp 8 providers
59 #150
DeepSeek V3.2 TEE 2 providers
59 #151
siliconflow/deepseek-v3.2 1 provider
59 #152
DeepSeek V3.2 (DeepInfra) 1 provider
59 #153
DeepSeek V3.2 (NovitaAI) 1 provider
59 #154
DeepSeek V3.2 (ByteDance) 1 provider
59 #155
DeepSeek V3.2 (Vertex AI (OpenAI-compatible)) 1 provider
59 #156
deepseek-ai/DeepSeek-V3.2 2 providers
59 #157
Pro/deepseek-ai/DeepSeek-V3.2 1 provider
59 #158
xAI Grok 3 1 provider
58 #159
Grok 3 1 provider
58 #160
Qwen3 14B Instruct 1 provider
58 #161
Kimi K2 0905 11 providers
57.3 #162
Kimi K2 (09/05) 1 provider
57.3 #163
Kimi K2 5 providers
57 #164
Kimi K2 Instruct 6 providers
57 #165
Kimi K2 0711 5 providers
57 #166
Kimi K2 (NovitaAI) 1 provider
57 #167
Gemini 2.5 Flash Preview (09/2025) 2 providers
56.7 #168
Gemini 3 Flash Preview 25 providers
55.7 #169
DeepSeek R1 Distill Qwen 14B 2 providers
55.7 #170
Gemini 3 Flash 3 providers
55.7 #171
DeepSeek/DeepSeek-V3.1-Terminus 1 provider
53.7 #172
DeepSeek V3.1 Terminus 7 providers
53.7 #173
R1 Distill Llama 70B 2 providers
53.7 #174
DeepSeek R1 Distill Llama 70B 5 providers
53.7 #175
siliconflow/deepseek-v3.1-terminus 1 provider
53.7 #176
deepseek-ai/DeepSeek-V3.1-Terminus 2 providers
53.7 #177
Pro/deepseek-ai/DeepSeek-V3.1-Terminus 1 provider
53.7 #178
Qwen3 Omni 30B A3B Instruct 1 provider
52.3 #179
DeepSeek-V3.1 20 providers
49.7 #180
deepseek-ai/DeepSeek-V3.1 1 provider
49.7 #181
Gemini 2.5 Flash Lite Preview (09/2025) 3 providers
46.7 #182
GPT-4.1 mini 23 providers
46.3 #183
GPT-4.1 Mini (OpenAI) 1 provider
46.3 #184
GPT-4.1 Mini (Azure) 1 provider
46.3 #185
OpenAI GPT-4.1 Mini 2 providers
46.3 #186
Z-AI/GLM 4.6 1 provider
44.3 #187
GLM-4.6 25 providers
44.3 #188
GLM-4.6 (NovitaAI) 1 provider
44.3 #189
GLM-4.6 (Z AI) 1 provider
44.3 #190
Zai GLM-4.6 1 provider
44.3 #191
x-AI/Grok-Code-Fast 1 1 provider
43.3 #192
grok-code-fast-1 5 providers
43.3 #193
xAI Grok Code Fast 1 1 provider
43.3 #194
x-AI/Grok-4-Fast 1 provider
41.3 #195
DeepSeek R1 Distill Llama 8B 1 provider
41.3 #196
Grok 4 Fast 1 provider
41.3 #197
baidu/ERNIE-4.5-300B-A47B 2 providers
41.3 #198
Magistral Small 3 providers
41.3 #199
DeepSeek-V3-0324 12 providers
41 #200
DeepSeek Chat 0324 1 provider
41 #201
siliconflow/deepseek-v3-0324 1 provider
41 #202
Magistral Medium (latest) 4 providers
40.3 #203
Qwen3 Coder 480B A35B Instruct 17 providers
39.3 #204
Qwen3 Coder 480B A35B 3 providers
39.3 #205
Qwen3 Coder 480B A35B Instruct (NovitaAI) 1 provider
39.3 #206
Qwen3 Coder 480B A35B Instruct (Vertex AI (OpenAI-compatible)) 1 provider
39.3 #207
Qwen/Qwen3-Coder-480B-A35B-Instruct 2 providers
39.3 #208
Claude 4.5 Haiku 3 providers
39 #209
Mistral Medium 3.1 5 providers
38.3 #210
Mistral Large 3 11 providers
38 #211
Claude 4.5 Sonnet 2 providers
37 #212
Claude Sonnet 4.5 (latest) 17 providers
37 #213
Claude Sonnet 4.5 19 providers
37 #214
Devstral 2 10 providers
36.7 #215
Gemini 2.5 Flash Lite 21 providers
35.3 #216
Gemini 2.5 Flash Lite (Google Vertex AI) 1 provider
35.3 #217
Gemini 2.5 Flash Lite (Google AI Studio) 1 provider
35.3 #218
Google Gemini 2.5 Flash Lite 1 provider
35.3 #219
GPT-4.1 26 providers
34.7 #220
GPT-4.1 (OpenAI) 1 provider
34.7 #221
GPT-4.1 (Azure) 1 provider
34.7 #222
OpenAI GPT-4.1 2 providers
34.7 #223
x-AI/Grok-4.1-Fast 1 provider
34.3 #224
Grok 4.1 Fast 2 providers
34.3 #225
Devstral Small 2 2 providers
34.3 #226
Reka Flash 3 2 providers
33.7 #227
Mistral Medium 3 10 providers
30.3 #228
Qwq 32B 4 providers
29 #229
Qwen3-Coder 30B-A3B Instruct 18 providers
29 #230
Qwen3 Coder 30B A3B Instruct (NovitaAI) 1 provider
29 #231
Qwen/Qwen3-Coder-30B-A3B-Instruct 2 providers
29 #232
Qwen3 VL 8B Instruct 2 providers
27.3 #233
Qwen/Qwen3-VL-8B-Instruct 3 providers
27.3 #234
Nemotron Nano 12B v2 VL 2 providers
26.7 #235
Nvidia Nemotron Nano 12B V2 VL 1 provider
26.7 #236
GLM 4.6V 12 providers
26.3 #237
GLM-4.6V (NovitaAI) 1 provider
26.3 #238
GLM-4.6V (Z AI) 1 provider
26.3 #239
DeepSeek-V3 12 providers
26 #240
deepseek-ai/DeepSeek-V3 2 providers
26 #241
Pro/deepseek-ai/DeepSeek-V3 1 provider
26 #242
GPT-4.1 nano 20 providers
24 #243
GPT-4.1 Nano (OpenAI) 1 provider
24 #244
GPT-4.1 Nano (Azure) 1 provider
24 #245
OpenAI GPT-4.1 Nano 1 provider
24 #246
Qwen3-235B-A22B-Instruct 3 providers
23.7 #247
DeepSeek R1 Distill Qwen 1.5B 1 provider
22 #248
Gemini 2.0 Flash 2 providers
21.7 #249
Claude 3.7 Sonnet 6 providers
21 #250
Gemma 3 27B 6 providers
20.7 #251
Gemma 3 27B (Nebius AI) 1 provider
20.7 #252
Llama 4 Maverick 4 providers
19.3 #253
Llama 4 Maverick 17B Instruct 5 providers
19.3 #254
Llama-4-Maverick-17B-128E-Instruct-FP8 5 providers
19.3 #255
Meta Llama 4 Maverick 17B 128E 1 provider
19.3 #256
Gemma 3 12B 4 providers
18.3 #257
Phi 4 4 providers
18 #258
GLM 4.5V 12 providers
15.3 #259
GLM-4.5V (NovitaAI) 1 provider
15.3 #260
GLM-4.5V (Z AI) 1 provider
15.3 #261
GPT-4o mini 20 providers
14.7 #262
GPT-4o Mini (OpenAI) 1 provider
14.7 #263
OpenAI GPT-4o mini 2 providers
14.7 #264
Llama 4 Scout 3 providers
14 #265
Qwen2.5 72B Instruct 4 providers
14 #266
Llama-4-Scout-17B-16E-Instruct-FP8 2 providers
14 #267
Meta Llama 4 Scout 17B 16E 1 provider
14 #268
Qwen/Qwen2.5-72B-Instruct 2 providers
14 #269
Qwen 2.5 72B Instruct 2 providers
14 #270
Granite-4.0-H-Small 1 provider
13.7 #271
nemotron-3-nano-30b-a3b 10 providers
13.3 #272
nvidia-nemotron-3-nano-30b-a3b 1 provider
13.3 #273
Nvidia Nemotron 3 Nano 30B 2 providers
13.3 #274
Command A 7 providers
13 #275
Nova Pro 3 providers
7 #276
Nova Lite 3 providers
7 #277
Phi-4-Mini 4 providers
6.7 #278
GPT-4o 21 providers
6 #279
Nova Micro 3 providers
6 #280
GPT-4o (OpenAI) 1 provider
6 #281
GPT-4o (Azure) 1 provider
6 #282
OpenAI GPT-4o 2 providers
6 #283
Mistral Large 2407 2 providers
0