P

Production library

46.6± 0.5 (95% CI)

Reference arm · pass rate 85.4% · simplicity 61.5

Runs

Each cell is one full attempt: the 3 implementers solve every problem with the task's production library. Click a cell to open that run.

TaskRun 1Run 2Run 3Mean ± std

arazu 40.1 38.0 41.339.8 ± 1.7

clirs 61.5 64.9 60.562.3 ± 2.3

heretical 44.1 43.5 43.343.6 ± 0.4

npr 46.4 46.2 50.547.7 ± 2.4

plaid 37.8 39.8 43.140.2 ± 2.7

pyda 57.9 59.1 57.858.3 ± 0.7

canon 60.9 59.4 59.159.8 ± 1.0

roadkill 29.0 25.7 28.727.8 ± 1.8

rubberband 67.5 66.7 65.366.5 ± 1.1

weft 30.6 29.9 32.931.1 ± 1.6

sapi 49.7 48.1 47.548.4 ± 1.1

simu 44.8 42.7 43.143.6 ± 1.1

uglypie 56.1 58.9 55.256.7 ± 1.9

umami 46.4 43.5 44.244.7 ± 1.5

wapi 27.2 32.8 27.329.1 ± 3.2