← Subnet 114 · test bench

gist_s1 · gistD

stage-1 pass

compressor variants/gist_novel_D.py · md5 cefc98901eda · 24/60 runs graded · tasks: django__django-12419, django__django-13821, django__django-14373, sympy__sympy-15875, sympy__sympy-19637 · other arms: gistA

Score
-0.031
90% CI -0.14 … +0.05
Weighted saving
+0.4%
pooled per run vs baseline
Resolved
8/8
baseline 7/8
Stage gates
S1 pass · S2 fail
tasks 5/5 (need 3)
Cost
$0.27
8 graded runs

Tokens per run vs baseline

bar = arm · tick = baseline · mean per graded run
Weighted157K of 158K↓ 0.4%
Fresh input34K of 22K↑ 51.4%
Cached input749K of 852K↓ 12.1%
Output16K of 17K↓ 3.4%
Steps23.5 of 25.2↓ 6.9%

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
django__django-124192/22/2121K158K-0.384maintain23 / 26526 / 700
django__django-138212/22/2225K186K+0.276maintain34 / 25638 / 758
django__django-143732/22/245K48K-0.103maintain14 / 13243 / 309
sympy__sympy-158750/11/1438K424K+0.046maintain49 / 471173 / 960
sympy__sympy-196371/11/141K47K-0.218maintain13 / 13183 / 264

Runs

16 runs incl. baseline
TaskArmRepResultSteps FreshCachedOutputWeightedTimeCost
django__django-12419baseliner1resolved2126K577K10K113K357s$0.023
django__django-12419baseliner2resolved2520K655K15K129K298s$0.027
django__django-12419gistDr1resolved2930K703K14K142K378s$0.030
django__django-12419gistDr2resolved2340K712K21K175K350s$0.042
django__django-13821baseliner1resolved4039K1.73M26K289K387s$0.053
django__django-13821baseliner2resolved2726K835K17K161K349s$0.033
django__django-13821gistDr1resolved2450K901K21K203K321s$0.046
django__django-13821gistDr2resolved2638K799K17K168K313s$0.036
django__django-14373baseliner1resolved1413K227K3K46K237s$0.009
django__django-14373baseliner2resolved1313K213K3K43K–$0.009
django__django-14373gistDr1resolved1216K206K5K51K216s$0.012
django__django-14373gistDr2resolved1414K221K3K45K–$0.009
sympy__sympy-15875baseliner1failed4928K2.37M57K438K639s$0.092
sympy__sympy-15875gistDr1resolved4766K2.22M45K424K593s$0.087
sympy__sympy-19637baseliner1resolved1313K206K2K41K196s$0.008
sympy__sympy-19637gistDr1resolved1315K223K3K47K194s$0.010