Humanity's Last Exam

Name: Humanity's Last Exam — AI Model Benchmark Results
Creator: Neura Market

Expert-level questions across diverse domains, designed to be the hardest public benchmark.

reasoning0-100 percent

Model Rankings (103)

#	Model	Score	Provider	Source
	Claude Fable 5.1🇺🇸			verified
	Claude Mythos Preview🇺🇸			verified
	Claude Opus 5🇺🇸			verified
	Claude Fable 5🇺🇸			verified
	Z GLM-5.3🇨🇳			verified
	M Muse Spark 1.1🇺🇸			verified
	DeepSeek-V4-Pro-0813🇨🇳			verified
	M Muse Spark🇺🇸			verified
	Claude Opus 4.8🇺🇸			verified
	Claude Sonnet 5🇺🇸			verified
	GPT-5.5 Pro🇺🇸			verified
	M Kimi K3🇨🇳			verified
	B Seed 2.1 Pro🇨🇳			verified
	Z GLM-5.3-Flash🇨🇳			verified
	Z GLM-5.2🇨🇳			verified
	Claude Opus 4.7🇺🇸			verified
	B Seed 2.1 Turbo🇨🇳			verified
	Claude Opus 4.6🇺🇸			verified
	Z GLM-5.1🇨🇳			verified
	GPT-5.5🇺🇸			verified
	Gemini 3.1 Pro🇺🇸			verified
	M Kimi K2-Thinking-0905🇨🇳			verified
	X Grok-4 Heavy🇺🇸			verified
	M Kimi K2.5🇨🇳			verified
	Claude Sonnet 4.6🇺🇸			verified
	Q Qwen3.5-27B🇨🇳			verified
	DeepSeek-V4-Pro-Max🇨🇳			verified
	Q Qwen3.5-122B-A10B🇨🇳			verified
	Q Qwen3.5-35B-A3B🇨🇳			verified
	Gemini 3 Pro🇺🇸			verified
	DeepSeek-V4-Flash-Max🇨🇳			verified
	Q Qwen3.8 Max🇨🇳			verified
	Gemini 3 Flash🇺🇸			verified
	Z GLM-4.7🇨🇳			verified
	Q Qwen3.7 Max🇨🇳			verified
	DeepSeek-V3.2🇨🇳			verified
	DeepSeek-V4-Flash-0423🇨🇳			verified
	Gemini 3.5 Flash🇺🇸			verified
	X Grok-4🇺🇸			verified
	GPT-5.4🇺🇸			verified
	ERNIE 5.0🇨🇳			verified
	Nemotron 3 Ultra (550B A55B)🇺🇸			verified
	GPT-5.2 Pro🇺🇸			verified
	M Kimi K2.6🇨🇳			verified
	Q Qwen3.8 Flash🇨🇳			verified
	Q Qwen3.8-Flash-Next🇨🇳			verified
	Q Qwen3.7-Plus🇨🇳			verified
	GPT-5.2🇺🇸			verified
	X MiMo-V2.5-Pro🇨🇳			verified
	T Inkling-Small🇺🇸			verified
	Q Qwen3.8-27B🇨🇳			verified
	DeepSeek-V3.2-Speciale🇨🇳			verified
	Q Qwen3.6 Plus🇨🇳			verified
	Q Qwen3.5-397B-A17B🇨🇳			verified
	GPT-5.4 mini🇺🇸			verified
	Gemma 4 31B🇺🇸			verified
	M LongCat-Flash-Thinking-2601🇨🇳			verified
	DeepSeek-V3.2 (Thinking)🇨🇳			verified
	GPT-5🇺🇸			verified
	GPT-5.4 nano🇺🇸			verified
	Q Qwen3.6-27B🇨🇳			verified
	Nemotron 3 Super (120B A12B)🇺🇸			verified
	X MiMo-V2-Flash🇨🇳			verified
	M Muse Glimmer-30B🇺🇸			verified
	MiniMax M2.1🇨🇳			verified
	Gemini 2.5 Pro Preview 06-05🇺🇸			verified
	Q Qwen3.6-35B-A3B🇨🇳			verified
	X Grok 4 Fast🇺🇸			verified
	DeepSeek-V3.2-Exp🇨🇳			verified
	Q Qwen3-235B-A22B-Thinking-2507🇨🇳			verified
	MAI-Code-1-Flash🇺🇸			verified
	Gemini 2.5 Pro🇺🇸			verified
	DeepSeek-R1-0528🇨🇳			verified
	Gemma 4 26B-A4B🇺🇸			verified
	Z GLM-4.6🇨🇳			verified
	GPT-5 mini🇺🇸			verified
	Gemini 3.1 Flash-Lite🇺🇸			verified
	DeepSeek-V3.1🇨🇳			verified
	Nemotron 3 Nano (30B A3B)🇺🇸			verified
	GPT OSS 120B🇺🇸			verified
	o4-mini🇺🇸			verified
	o3🇺🇸			verified
	Z GLM-4.5🇨🇳			verified
	Z GLM-4.7-Flash🇨🇳			verified
	Q Qwen3 VL 235B A22B Thinking🇨🇳			verified
	MiniMax M2🇨🇳			verified
	DiffusionGemma 26B-A4B🇺🇸			verified
	Nemotron 3.5 Lightning (30B A3B)🇺🇸			verified
	S Sarvam-105B🇮🇳			verified
	Gemini 2.5 Flash🇺🇸			verified
	GPT OSS 20B🇺🇸			verified
	Z GLM-4.5-Air🇨🇳			verified
	Magistral Medium🇫🇷			verified
	GPT-5 nano🇺🇸			verified
	MiniMax M1 80K🇨🇳			verified
	MiniMax M1 40K🇨🇳			verified
	GPT-4.1🇺🇸			verified
	GPT-4o🇺🇸			verified
	Gemma 4 12B🇺🇸			verified
	Gemini 2.5 Flash-Lite🇺🇸			verified
	M Kimi K2 Instruct🇨🇳			verified
	M Kimi K2-Instruct-0905🇨🇳			verified
	GPT-4.1 mini🇺🇸			verified

AI Model Benchmarks

Humanity's Last Exam

Model Rankings (103)