FlagEval

non-profit

https://flageval.baai.ac.cn/

AI & ML interests

None defined yet.

Recent Activity

eyuansu71 authored a paper about 2 months ago

MoM: Memory of Memory

eyuansu71 submitted a paper about 2 months ago

ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals

eyuansu71 authored a paper about 2 months ago

ImpossibleRubrics: Stress-Testing Generated Rubrics as Reward Signals

View all activity

FlagEval 's datasets 13

FlagEval/ERQAPlus

Viewer • Updated Jun 22 • 800 • 87 • 1

FlagEval/coco_val2014_sampled

Viewer • Updated Nov 6, 2025 • 1k • 31

FlagEval/MeasureBench

Viewer • Updated Nov 3, 2025 • 2.44k • 775 • 6

FlagEval/EmbodiedVerse-Bench

Viewer • Updated Jun 25, 2025 • 2.04k • 266

FlagEval/Where2Place

Viewer • Updated May 29, 2025 • 100 • 679

FlagEval/SAT

Viewer • Updated May 6, 2025 • 150 • 148

FlagEval/HMMT_2025

Viewer • Updated May 6, 2025 • 30 • 128 • 1

FlagEval/ERQA

Viewer • Updated Apr 22, 2025 • 400 • 2.54k • 6

FlagEval/sub_spatial

Viewer • Updated Apr 21, 2025 • 690 • 131

FlagEval/EmbSpatial-Bench

Viewer • Updated Apr 21, 2025 • 3.64k • 3.75k • 6

FlagEval/documentation-images

Viewer • Updated Nov 13, 2024 • 3 • 177

FlagEval/CLCC_v1

Viewer • Updated Jul 29, 2024 • 760 • 55 • 3

FlagEval/HalluDial

Updated Jun 26, 2024 • 39 • 4