← Subnet 114 · test bench

ablB · comments

stage-1 fail

compressor variants/ablation/ablate_comments.py · md5 6344f621186e · 27/27 runs graded · tasks: conan-io__conan-20032, django__django-13417, getmoto__moto-10057 · other arms: grephits

Score
-0.135
90% CI -0.35 … +0.09
Weighted saving
-22.9%
pooled per run vs baseline
Resolved
6/9
baseline 6/9
Stage gates
S1 fail · S2 fail
tasks 2/3 (need 2)
Cost
$0.30
9 graded runs

Tokens per run vs baseline

bar = arm · tick = baseline · mean per graded run
Weighted207K of 169K↑ 22.9%
Fresh input29K of 29K↓ 0.6%
Cached input1.36M of 1.04M↑ 31.1%
Output14K of 12K↑ 17.9%
Steps42.1 of 33.7↑ 25.1%

Tasks

x = baseline resolves · y = arm resolves · r = log2(W base / W arm)
TaskBase x/nArm y/nW baseW armrZoneSteps b / aOut/step b / a
conan-io__conan-200320/30/3177K216K-0.290none31 / 40482 / 401
django__django-134173/33/387K101K-0.207maintain19 / 25366 / 318
getmoto__moto-100573/33/3242K305K-0.334maintain51 / 61283 / 290

Runs

18 runs incl. baseline
TaskArmRepResultSteps FreshCachedOutputWeightedTimeCost
conan-io__conan-20032baseliner1failed2831K823K10K143K125s$0.026
conan-io__conan-20032baseliner2failed2933K1.01M21K196K191s$0.041
conan-io__conan-20032baseliner3failed3532K1.20M13K192K192s$0.033
conan-io__conan-20032commentsr1failed3333K990K10K163K162s$0.028
conan-io__conan-20032commentsr2failed3329K992K14K169K175s$0.031
conan-io__conan-20032commentsr3failed5534K2.05M26K317K330s$0.054
django__django-13417baseliner1resolved1520K331K6K71K286s$0.015
django__django-13417baseliner2resolved3025K787K10K134K255s$0.024
django__django-13417baseliner3resolved1317K257K5K57K220s$0.012
django__django-13417commentsr1resolved2519K559K8K101K306s$0.019
django__django-13417commentsr2resolved1515K286K5K58K206s$0.012
django__django-13417commentsr3resolved3523K888K11K144K272s$0.025
getmoto__moto-10057baseliner1resolved5232K1.71M14K246K261s$0.037
getmoto__moto-10057baseliner2resolved4635K1.40M13K213K240s$0.034
getmoto__moto-10057baseliner3resolved5535K1.85M16K268K682s$0.041
getmoto__moto-10057commentsr1resolved8640K3.37M24K450K831s$0.061
getmoto__moto-10057commentsr2resolved3928K1.06M11K167K212s$0.028
getmoto__moto-10057commentsr3resolved5837K2.09M18K300K1049s$0.045