facebook/anli
Viewer • Updated • 169k • 15.3k • 50
LLM evaluation datasets
-
-
codeparrot/apps
Updated • 15.1k • 202 -
allenai/ai2_arc
Viewer • Updated • 7.79k • 493k • 346 -
EleutherAI/asdiv
Viewer • Updated • 2.31k • 2.06k • 6 -
facebook/babi_qa
Viewer • Updated • 10.4k • 1.88k • 12 -
heegyu/bbq
Viewer • Updated • 58.5k • 23.6k • 24 -
nyu-mll/blimp
Viewer • Updated • 67k • 28.9k • 38 -
AmazonScience/bold
Viewer • Updated • 7.2k • 1.41k • 19 -
google/boolq
Viewer • Updated • 12.7k • 54.1k • 100 -
cam-cst/cbt
Viewer • Updated • 687k • 3.34k • 16 -
aps/super_glue
Viewer • Updated • 196k • 194k • 188 -
nyu-mll/glue
Viewer • Updated • 1.49M • 492k • 498 -
google/civil_comments
Viewer • Updated • 2M • 8.13k • 31 -
abisee/cnn_dailymail
Viewer • Updated • 936k • 180k • 344 -
tuetschek/e2e_nlg_cleaned
Updated • 765 • 3 -
tau/commonsense_qa
Viewer • Updated • 12.1k • 60.4k • 149 -
stanfordnlp/coqa
Viewer • Updated • 7.7k • 4.74k • 85 -
ucinlp/drop
Viewer • Updated • 86.9k • 9.91k • 68 -
lighteval/DyckLanguage
Viewer • Updated • 1.51k • 83 -
openai/gsm8k
Benchmark • Updated • 17.6k • 969k • 1.34k -
Rowan/hellaswag
Viewer • Updated • 60k • 300k • 176 -
openai/openai_humaneval
Viewer • Updated • 164 • 305k • 388 -
stanfordnlp/imdb
Viewer • Updated • 100k • 205k • 374 -
cimec/lambada
Viewer • Updated • 12.7k • 62.2k • 65 -
lighteval/LegalSupport
Viewer • Updated • 20k • 78 • 1 -
lighteval/lsat_qa
Viewer • Updated • 459 • 137 • 4 -
deepmind/math_dataset
Updated • 3.78k • 139 -
deepmind/aqua_rat
Viewer • Updated • 196k • 8.15k • 72 -
google-research-datasets/mbpp
Viewer • Updated • 1.4k • 215k • 230 -
cais/mmlu
Viewer • Updated • 231k • 557k • 749 -
microsoft/ms_marco
Viewer • Updated • 1.11M • 24.8k • 242 -
CogComp/trec
Updated • 10.9k • 48 -
Open ASR Leaderboard
🏆1.35kCompare speech‑to‑text models across multiple benchmarks