Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

IFEval

Instruction Following Evaluation — measures how well models follow complex multi-step instructions

general0-100 percentPaper / Website

Model Rankings (17)

#	Model	Score	Provider	Source
	Claude Opus 4🇺🇸			aggregated
	Claude Sonnet 4🇺🇸			aggregated
	Claude 3.5 Sonnet🇺🇸			aggregated
	Llama 3.1 405B🇺🇸			aggregated
	o1🇺🇸			aggregated
	Llama 3.3 70B🇺🇸			aggregated
	Claude 3 Opus🇺🇸			aggregated
	Qwen 2.5 72B🇨🇳			aggregated
	GPT-4o🇺🇸			aggregated
	Llama 3.1 70B🇺🇸			aggregated
	Mistral Large 2🇫🇷			aggregated
	GPT-4 Turbo🇺🇸			aggregated
	GPT-4o mini🇺🇸			aggregated
	Claude 3.5 Haiku🇺🇸			aggregated
	Command R+🇨🇦			aggregated
	Llama 3.1 8B🇺🇸			aggregated
	Mixtral 8x22B🇫🇷			aggregated

IFEval — AI Model Leaderboard & Results | Neura Market