MMLU-Pro - a TIGER-Lab Collection

TIGER-Lab 's Collections

MoCha

General-Reasoner

Vamba

ABC

VisualWebInstruct

CritiqueFineTuning

VISTA

VLM2Vec

MAmmoTH

UniIR

Science

Mantis

MMLU-Pro

updated about 11 hours ago

MMLU-Pro

TIGER-Lab/MMLU-Pro

Viewer • Updated Apr 6 • 12.1k • 56.7k • 365
Running on CPU Upgrade

217

217

MMLU-Pro Leaderboard

🥇

More advanced and challenging multi-task evaluation
TIGER-Lab/mmlu_pro_leaderboard_submission

Viewer • Updated 1 day ago • 216 • 162