HumaniBench Leaderboard

Aggregate accuracy (%) per Human-Centric principle across all relevant tasks. Higher is better. Click model names to visit their official pages.

#	Model	Org	Params	Type	Fairness	Ethics	Understanding	Reasoning	Language	Empathy	Robustness	Overall
🥇	DeepSeek-VL2-Small	Microsoft	5.6B	Closed	61.0%	98.9%	73.5%	78.8%	62.2%	89.5%	57.2%	74.4%

Overall = mean of all 7 principle scores. -- indicates data not yet available.