Running
1.07k
📈
Code LMs Benchmark
-
-
Running430🏆
Can Ai Code Results
-
openai/openai_humaneval
Viewer • Updated • 164 • 60k • 258 -
google-research-datasets/mbpp
Viewer • Updated • 1.4k • 53.3k • 152 -
nuprl/MultiPL-E
Viewer • Updated • 12.7k • 205k • 46 -
evalplus/mbppplus
Viewer • Updated • 378 • 27.7k • 8 -
BAAI/TACO
Updated • 1.3k • 87 -
princeton-nlp/SWE-bench
Viewer • Updated • 21.5k • 13.6k • 93 -
codeparrot/apps
Viewer • Updated • 20k • 4.81k • 141 -
cruxeval-org/cruxeval
Viewer • Updated • 800 • 1.11k • 14 -
tianyang/repobench_python_v1.1
Viewer • Updated • 23.6k • 422 • 7 -
SciPhi/textbooks-are-all-you-need-lite
Viewer • Updated • 682k • 294 • 180 -
nampdn-ai/tiny-codes
Viewer • Updated • 1.63M • 204 • 236 -
allenai/math_qa
Updated • 23.6k • 94 -
deepmind/code_contests
Viewer • Updated • 4.04k • 7.43k • 131 -
FudanSELab/ClassEval
Viewer • Updated • 100 • 287 • 8 -
ML4SE2023-G1-WizardCoder/ML4SE23_G1_MBCPP-SCoT
Viewer • Updated • 870 • 46 -
Muennighoff/quixbugs
Viewer • Updated • 40 • 59 -
bigcode/humanevalpack
Updated • 9.2k • 75 -
NTU-NLP-sg/xCodeEval
Updated • 43.1k • 40 -
JetBrains-Research/commit-chronicle
Viewer • Updated • 10.9M • 3.83k • 7 -
tianyang/repobench_java_v1.1
Viewer • Updated • 26.1k • 254 -
zijwang/CrossCodeEval
Updated • 37