AIME 2025

Name: AIME 2025 — AI Model Benchmark Results
Creator: Neura Market

American Invitational Mathematics Examination 2025 — competition-level math problems.

math0-100 percent

Model Rankings (119)

#	Model	Score	Provider	Source
	GPT-5.2🇺🇸			verified
	Gemini 3 Pro🇺🇸			verified
	X Grok-4 Heavy🇺🇸			verified
	M Kimi K2-Thinking-0905🇨🇳			verified
	GPT-5.2 Pro🇺🇸			verified
	Claude Opus 4.6🇺🇸			verified
	Gemini 3 Flash🇺🇸			verified
	M LongCat-Flash-Thinking-2601🇨🇳			verified
	GPT-5.1 High🇺🇸			verified
	Nemotron 3 Nano (30B A3B)🇺🇸			verified
	GPT OSS 20B High🇺🇸			verified
	GPT-5.1 Medium🇺🇸			verified
	B Seed 2.0 Pro🇨🇳			verified
	S Step-3.5-Flash🇨🇳			verified
	MAI-Thinking-1🇺🇸			verified
	GPT-5.1 Codex High🇺🇸			verified
	S Sarvam-30B🇮🇳			verified
	S Sarvam-105B🇮🇳			verified
	M Kimi K2.5🇨🇳			verified
	DeepSeek-V3.2-Speciale🇨🇳			verified
	Z GLM-4.7🇨🇳			verified
	GPT-5🇺🇸			verified
	GPT-5 High🇺🇸			verified
	X MiMo-V2-Flash🇨🇳			verified
	GPT-5.1 Thinking🇺🇸			verified
	GPT-5.1🇺🇸			verified
	GPT-5.1 Instant🇺🇸			verified
	Z GLM-4.6🇨🇳			verified
	X Grok-3🇺🇸			verified
	DeepSeek-V3.2🇨🇳			verified
	DeepSeek-V3.2 (Thinking)🇨🇳			verified
	B Seed 2.0 Lite🇨🇳			verified
	L EXAONE 4.5 33B🇰🇷			verified
	L K-EXAONE-236B-A23B🇰🇷			verified
	o4-mini🇺🇸			verified
	GPT OSS 120B High🇺🇸			verified
	Nova 2 Pro🇺🇸			verified
	Q Qwen3-235B-A22B-Thinking-2507🇨🇳			verified
	Nova 2 Omni🇺🇸			verified
	X Grok 4 Fast🇺🇸			verified
	X Grok-4🇺🇸			verified
	Z GLM-4.7-Flash🇨🇳			verified
	I Mercury 2🇺🇸			verified
	GPT-5 mini🇺🇸			verified
	Nova 2 Lite🇺🇸			verified
	X Grok-3 Mini🇺🇸			verified
	M LongCat-Flash-Thinking🇨🇳			verified
	Nemotron 3 Super (120B A12B)🇺🇸			verified
	Command A+🇨🇦			verified
	Q Qwen3 VL 235B A22B Thinking🇨🇳			verified
	DeepSeek-V3.2-Exp🇨🇳			verified
	I IBM Granite 4.2 30B🇺🇸			verified
	GPT-5 Medium🇺🇸			verified
	Gemini 2.5 Pro Preview 06-05🇺🇸			verified
	Q Qwen3-Next-80B-A3B-Thinking🇨🇳			verified
	S Step3-VL-10B🇨🇳			verified
	DeepSeek-R1-0528🇨🇳			verified
	Claude Sonnet 4.5🇺🇸			verified
	ERNIE 5.0🇨🇳			verified
	I IBM Granite 4.2 8B🇺🇸			verified
	o3🇺🇸			verified
	Mistral Medium 3.5🇫🇷			verified
	GPT-5 nano🇺🇸			verified
	Ministral 3 (14B Reasoning 2512)🇫🇷			verified
	Mistral Small 4🇫🇷			verified
	Q Qwen3 VL 32B Thinking🇨🇳			verified
	Q Qwen3 VL 30B A3B Thinking🇨🇳			verified
	Gemini 2.5 Pro🇺🇸			verified
	Q Qwen3 Max🇨🇳			verified
	Q Qwen3 235B A22B🇨🇳			verified
	GPT-5.5 Instant🇺🇸			verified
	MiniMax M2.1🇨🇳			verified
	Claude Haiku 4.5🇺🇸			verified
	Q Qwen3 VL 8B Thinking🇨🇳			verified
	Ministral 3 (8B Reasoning 2512)🇫🇷			verified
	O MiniCPM-SALA🇨🇳			verified
	I IBM Granite 4.2 3B🇺🇸			verified
	MiniMax M2🇨🇳			verified
	Claude Opus 4.1🇺🇸			verified
	Phi 4 Reasoning Plus🇺🇸			verified
	MiniMax M1 80K🇨🇳			verified
	Claude Opus 4🇺🇸			verified
	Q Qwen3 VL 235B A22B Instruct🇨🇳			verified
	MiniMax M1 40K🇨🇳			verified
	Q Qwen3 VL 4B Thinking🇨🇳			verified
	Q Qwen3 32B🇨🇳			verified
	Llama 3.1 Nemotron Ultra 253B v1🇺🇸			verified
	Min istral 3 (3B Reasoning 2512)🇫🇷			verified
	Nemotron Nano 9B v2🇺🇸			verified
	Gemini 2.5 Flash🇺🇸			verified
	Q Qwen3 30B A3B🇨🇳			verified
	Claude Sonnet 4🇺🇸			verified
	Q Qwen3-235B-A22B-Instruct-2507🇨🇳			verified
	Q Qwen3-Next-80B-A3B-Instruct🇨🇳			verified
	Q Qwen3 VL 30B A3B Instruct🇨🇳			verified
	Q Qwen3 VL 32B Instruct🇨🇳			verified
	Magistral Medium🇫🇷			verified
	M LongCat-Flash-Lite🇨🇳			verified
	Phi 4 Reasoning🇺🇸			verified
	Magistral Small 2506🇫🇷			verified
	M LongCat-Flash-Chat🇨🇳			verified
	Llama-3.3 Nemotron Super 49B v1🇺🇸			verified
	Claude 3.7 Sonnet🇺🇸			verified
	L LFM2.5-2.6B🇺🇸			verified
	DeepSeek-V3.1🇨🇳			verified
	Gemini 2.5 Flash-Lite🇺🇸			verified
	M Kimi K2 Instruct🇨🇳			verified
	M Kimi K2-Instruct-0905🇨🇳			verified
	Llama 3.1 Nemotron Nano 8B V1🇺🇸			verified
	Q Qwen3 VL 4B Instruct🇨🇳			verified
	GPT-4.1🇺🇸			verified
	Q Qwen3 VL 8B Instruct🇨🇳			verified
	GPT-5.1 Codex Mini🇺🇸			verified
	GPT-4.1 mini🇺🇸			verified
	Gemini Diffusion🇺🇸			verified
	Gemma 3n E4B Instructed LiteRT Preview🇺🇸			verified
	Gemma 3n E4B Instructed🇺🇸			verified
	Gemma 3n E2B Instructed LiteRT (Preview)🇺🇸			verified
	Gemma 3n E2B Instructed🇺🇸			verified

AI Model Benchmarks

AIME 2025

Model Rankings (119)