benchlm.ai

American Invitational Mathematics Examination 2024 (AIME 2024)

The 2024 edition of AIME, maintaining the same format of 15 challenging mathematics problems with integer answers from 000 to 999.

About AIME 2024

Year

2024

Tasks

15 problems

Format

Integer answers 000-999

Difficulty

High school olympiad level

AIME 2024 continues the tradition of challenging mathematical reasoning problems. These problems test deep understanding of mathematical concepts and creative problem-solving abilities.

American Invitational Mathematics Examination

Leaderboard (88 models)

#1GPT-5.4
99
#2Gemini 3.1 Pro
99
#3Claude Opus 4.6
99
#4GPT-5.3 Codex
99
#5Grok 4.1
99
#6GPT-5.2
99
#7GPT-5.2-Codex
99
#8Gemini 3 Pro Deep Think
99
#9Claude Sonnet 4.6
99
#10Claude Opus 4.5
99
#11Gemini 3 Pro
99
#12GPT-5.1-Codex-Max
99
#13GPT-5.1
99
#14GLM-5 (Reasoning)
99
#15Claude Sonnet 4.5
99
#16Grok 4.1 Fast
98
#17GPT-5 (high)
97
#18o1-preview
96
#19Kimi K2.5 (Reasoning)
96
#20GPT-5 (medium)
95
#21Qwen3.5 397B (Reasoning)
95
#22GPT-5 mini
92
#23o3-pro
92
#24o3
90
#25GLM-5
90
#26Grok 4
89
#27DeepSeek V3.2 (Thinking)
89
#28GLM-4.7
88
#29Qwen2.5-1M
87
#30Qwen2.5-72B
86
#31Gemini 2.5 Pro
86
#32DeepSeek V3.2
86
#33o4-mini (high)
85
#34Qwen3.5 397B
85
#35DeepSeek Coder 2.0
83
#36DeepSeek LLM 2.0
82
#37DeepSeekMath V2
82
#38MiMo-V2-Flash
81
#39Kimi K2.5
79
#40Claude 4.1 Opus
78
#41Mistral Large 3
78
#42Nemotron 3 Ultra 500B
76
#43Claude 4 Sonnet
75
#44MiniMax M2.5
75
#45Llama 3.1 405B
72
#46Gemini 3 Flash
72
#47Mistral Large 2
70
#48Claude Haiku 4.5
70
#49GPT-4o
68
#50GLM-4.7-Flash
68
#51Mistral 8x7B
67
#52Claude 3.5 Sonnet
67
#53Nemotron 3 Super 100B
67
#54Gemini 1.5 Pro
66
#55Grok Code Fast 1
66
#56Gemini 3.1 Flash-Lite
65
#57Gemini 1.0 Pro
64
#58Claude 3 Opus
63
#59GPT-4 Turbo
62
#60Llama 3 70B
60
#61Nemotron 3 Nano 30B
59
#62Claude 3 Haiku
58
#63Nemotron-4 15B
56
#64Moonshot v1
55
#65Z-1
54
#66GPT-OSS 120B
53
#67Gemini 2.5 Flash
52
#68Nemotron Ultra 253B
51
#69Llama 4 Behemoth
50
#70Llama 4 Scout
49
#71Llama 4 Maverick
48
#72Gemma 3 27B
47
#73DeepSeek-R1
46
#74Qwen2.5-VL-32B
45
#75Grok 3 [Beta]
44
#76Nova Pro
43
#77Qwen3 235B 2507 (Reasoning)
42
#78Qwen3 235B 2507
41
#79Claude 4.1 Opus Thinking
40
#80GLM-4.5
39
#81MiniMax M1 80k
38
#82GLM-4.5-Air
37
#83DeepSeek V3.1 (Reasoning)
36
#84DeepSeek V3.1
35
#85Kimi K2
34
#86GPT-OSS 20B
33
#87Mistral 7B v0.3
32
#88Mistral 8x7B v0.2
31

FAQ

What does AIME 2024 measure?

The 2024 edition of AIME, maintaining the same format of 15 challenging mathematics problems with integer answers from 000 to 999.

Which model scores highest on AIME 2024?

GPT-5.4 by OpenAI currently leads with a score of 99 on AIME 2024.

How many models are evaluated on AIME 2024?

88 AI models have been evaluated on AIME 2024 on BenchLM.