benchlm.ai

Harvard-MIT Mathematics Tournament February 2025 (HMMT Feb 2025)

The most recent February edition of the Harvard-MIT Mathematics Tournament, featuring the latest challenging problems in competitive mathematics.

About HMMT Feb 2025

Year

2025

Tasks

Tournament problems

Format

Competition mathematics

Difficulty

High school olympiad level

HMMT Feb 2025 represents the current pinnacle of high school mathematics competition, with problems designed to challenge the brightest mathematical minds.

Harvard-MIT Mathematics Tournament

Leaderboard (88 models)

#1GPT-5.4
96
#2Gemini 3.1 Pro
96
#3Claude Opus 4.6
96
#4GPT-5.3 Codex
96
#5Grok 4.1
96
#6GPT-5.2
96
#7GPT-5.2-Codex
96
#8Gemini 3 Pro Deep Think
96
#9Claude Sonnet 4.6
96
#10Claude Opus 4.5
96
#11Gemini 3 Pro
96
#12GPT-5.1-Codex-Max
96
#13GPT-5.1
96
#14GLM-5 (Reasoning)
95
#15Claude Sonnet 4.5
94
#16Grok 4.1 Fast
93
#17GPT-5 (high)
92
#18o1-preview
91
#19Kimi K2.5 (Reasoning)
91
#20GPT-5 (medium)
90
#21Qwen3.5 397B (Reasoning)
90
#22GPT-5 mini
87
#23o3-pro
87
#24Grok 4
85
#25o3
85
#26GLM-5
85
#27DeepSeek V3.2 (Thinking)
84
#28GLM-4.7
83
#29Qwen2.5-1M
82
#30Qwen2.5-72B
81
#31Gemini 2.5 Pro
81
#32DeepSeek V3.2
81
#33o4-mini (high)
80
#34Qwen3.5 397B
80
#35DeepSeek Coder 2.0
78
#36DeepSeek LLM 2.0
77
#37DeepSeekMath V2
77
#38MiMo-V2-Flash
76
#39Kimi K2.5
74
#40Claude 4.1 Opus
73
#41Mistral Large 3
73
#42Nemotron 3 Ultra 500B
71
#43Claude 4 Sonnet
70
#44MiniMax M2.5
70
#45Llama 3.1 405B
67
#46Gemini 3 Flash
67
#47Mistral Large 2
65
#48Claude Haiku 4.5
65
#49GPT-4o
63
#50GLM-4.7-Flash
63
#51Mistral 8x7B
62
#52Claude 3.5 Sonnet
62
#53Nemotron 3 Super 100B
62
#54Gemini 1.5 Pro
61
#55Grok Code Fast 1
61
#56Gemini 3.1 Flash-Lite
60
#57Gemini 1.0 Pro
59
#58Claude 3 Opus
58
#59GPT-4 Turbo
57
#60Llama 3 70B
55
#61Nemotron 3 Nano 30B
54
#62Claude 3 Haiku
53
#63Nemotron-4 15B
51
#64Moonshot v1
50
#65Z-1
49
#66GPT-OSS 120B
48
#67Gemini 2.5 Flash
47
#68Nemotron Ultra 253B
46
#69Llama 4 Behemoth
45
#70Llama 4 Scout
44
#71Llama 4 Maverick
43
#72Gemma 3 27B
42
#73DeepSeek-R1
41
#74Qwen2.5-VL-32B
40
#75Grok 3 [Beta]
39
#76Nova Pro
38
#77Qwen3 235B 2507 (Reasoning)
37
#78Qwen3 235B 2507
36
#79Claude 4.1 Opus Thinking
35
#80GLM-4.5
34
#81MiniMax M1 80k
33
#82GLM-4.5-Air
32
#83DeepSeek V3.1 (Reasoning)
31
#84DeepSeek V3.1
30
#85Kimi K2
29
#86GPT-OSS 20B
28
#87Mistral 7B v0.3
27
#88Mistral 8x7B v0.2
26

FAQ

What does HMMT Feb 2025 measure?

The most recent February edition of the Harvard-MIT Mathematics Tournament, featuring the latest challenging problems in competitive mathematics.

Which model scores highest on HMMT Feb 2025?

GPT-5.4 by OpenAI currently leads with a score of 96 on HMMT Feb 2025.

How many models are evaluated on HMMT Feb 2025?

88 AI models have been evaluated on HMMT Feb 2025 on BenchLM.