cais/hle
Benchmark • Updated • 2.5k • 44.7k • 757
Benchmark datasets
-
-
Qwen/DeepPlanning
Viewer • Updated • 2.14k • 706 • 193 -
gaia-benchmark/GAIA
Viewer • Updated • 932 • 33.8k • 634 -
BLINK-Benchmark/BLINK
Viewer • Updated • 3.81k • 15.3k • 41 -
openai/gsm8k
Benchmark • Updated • 17.6k • 758k • 1.23k -
allenai/olmOCR-bench
Benchmark • Updated • 3.44k • 168 -
TIGER-Lab/MMLU-Pro
Benchmark • Updated • 12.1k • 125k • 461 -
openai/openai_humaneval
Viewer • Updated • 164 • 244k • 376 -
Muennighoff/mbpp
Viewer • Updated • 1.4k • 1.9k • 22 -
bigcode/bigcodebench
Viewer • Updated • 5.7k • 40.8k • 77 -
livecodebench/test_generation
Viewer • Updated • 442 • 1.17k • 7 -
ScaleAI/SWE-bench_Pro
Benchmark • Updated • 731 • 834k • 70 -
SWE-bench/SWE-bench_Verified
Benchmark • Updated • 500 • 120k • 24 -
mteb/arguana
Benchmark • Updated • 11.5k • 11.8k • 5 -
MathArena/hmmt_feb_2026
Benchmark • Updated • 33 • 1.53k • 1 -
Idavidrein/gpqa
Benchmark • Updated • 1.25k • 111k • 407 -
likaixin/ScreenSpot-Pro
Benchmark • Updated • 5.94k • 60 -
harborframework/terminal-bench-2.0
Benchmark • Updated • 2.47k • 18 -
FutureMa/EvasionBench
Benchmark • Updated • 16.7k • 167 • 84 -
internlm/WildClawBench
Updated • 8.59k • 46 -
FINAL-Bench/World-Model
Viewer • Updated • 100 • 1.25k • 25