MMMLU

Name: MMMLU — AI Model Benchmark Results
Creator: Neura Market

Multilingual Massive Multitask Language Understanding across many languages.

general0-100 percent

Model Rankings (49)

#	Model	Score	Provider	Source
	Claude Mythos Preview🇺🇸			verified
	Gemini 3.1 Pro🇺🇸			verified
	Gemini 3 Pro🇺🇸			verified
	Gemini 3 Flash🇺🇸			verified
	Claude Opus 4.7🇺🇸			verified
	Claude Opus 4.6🇺🇸			verified
	Claude Opus 4.5🇺🇸			verified
	Q Qwen3.7 Max🇨🇳			verified
	GPT-5.2🇺🇸			verified
	Claude Opus 4.1🇺🇸			verified
	Q Qwen3.6 Plus🇨🇳			verified
	Claude Sonnet 4.6🇺🇸			verified
	Claude Sonnet 4.5🇺🇸			verified
	Q Qwen3.7-Plus🇨🇳			verified
	Gemini 3.1 Flash-Lite🇺🇸			verified
	Claude Opus 4🇺🇸			verified
	Q Qwen3.5-397B-A17B🇨🇳			verified
	Gemma 4 31B🇺🇸			verified
	o1🇺🇸			verified
	GPT-4.1🇺🇸			verified
	Q Qwen3 235B A22B🇨🇳			verified
	Q Qwen3.5-122B-A10B🇨🇳			verified
	Claude Sonnet 4🇺🇸			verified
	Gemma 4 26B-A4B🇺🇸			verified
	Claude 3.7 Sonnet🇺🇸			verified
	Q Qwen3.5-27B🇨🇳			verified
	L K-EXAONE-236B-A23B🇰🇷			verified
	Mistral Large 3 (675B Base)🇫🇷			verified
	Mistral Large 3 (675B Instruct 2512 Eagle)🇫🇷			verified
	Mistral Large 3 (675B Instruct 2512 NVFP4)🇫🇷			verified
	Mistral Large 3 (675B Instruct 2512)🇫🇷			verified
	Q Qwen3.5-35B-A3B🇨🇳			verified
	GPT-4.5🇺🇸			verified
	GPT OSS 120B High🇺🇸			verified
	Gemma 4 12B🇺🇸			verified
	Claude Haiku 4.5🇺🇸			verified
	DiffusionGemma 26B-A4B🇺🇸			verified
	GPT-4o🇺🇸			verified
	Q Qwen3.5-9B🇨🇳			verified
	GPT-4.1 mini🇺🇸			verified
	Gemma 4 E4B🇺🇸			verified
	Q Qwen3.5-4B🇨🇳			verified
	Mistral Large 3🇫🇷			verified
	Phi-3.5-MoE-instruct🇺🇸			verified
	Gemma 4 E2B🇺🇸			verified
	GPT-4.1 nano🇺🇸			verified
	Q Qwen3.5-2B🇨🇳			verified
	Phi-3.5-mini-instruct🇺🇸			verified
	Q Qwen3.5-0.8B🇨🇳			verified

AI Model Benchmarks

MMMLU

Model Rankings (49)