← Subnet 114 · test bench

past01 · baseline

baseline

compressor identity (no compression) · md5 2f366ecc33ee · 70/32 runs graded · tasks: 567-labs__instructor-2259, apify__crawlee-python-1976, conan-io__conan-20032, conan-io__conan-20078, conan-io__conan-20136, conan-io__conan-20146, conan-io__conan-20208, conan-io__conan-20217, dask__dask-12301, dask__dask-12430, falconry__falcon-2673, falconry__falcon-2682, getmoto__moto-10007, getmoto__moto-10012, getmoto__moto-10028, getmoto__moto-10041, getmoto__moto-10057, getmoto__moto-10067, getmoto__moto-10070, getmoto__moto-10093, getmoto__moto-10117, getmoto__moto-10127, getmoto__moto-10146, getmoto__moto-10170, jd__tenacity-606, jd__tenacity-615, jd__tenacity-640, jd__tenacity-653, keephq__keep-6611, keephq__keep-6638, livekit__agents-6625, mvt-project__mvt-815, nltk__nltk-3580, sktime__sktime-10583, vega__altair-4019

Score
–
–
Weighted saving
–
pooled per run vs baseline
Resolved
45/70
baseline 45/70
Stage gates
–
Cost
$3.86
70 graded runs

Tokens per run vs baseline

bar = arm · tick = baseline · mean per graded run
Weighted338K of 338K↑ 0.0%
Fresh input38K of 38K↑ 0.0%
Cached input2.24M of 2.24M↑ 0.0%
Output25K of 25K↑ 0.0%
Steps48.8 of 48.8↑ 0.0%

Runs

70 runs incl. baseline
TaskArmRepResultSteps FreshCachedOutputWeightedTimeCost
567-labs__instructor-2259baseliner1resolved1020K177K1K42K256s$0.009
567-labs__instructor-2259baseliner2resolved812K146K2K32K277s$0.007
apify__crawlee-python-1976baseliner1resolved1625K382K7K83K343s$0.018
apify__crawlee-python-1976baseliner2resolved2625K786K13K143K395s$0.028
conan-io__conan-20032baseliner1failed4036K1.51M19K246K930s$0.043
conan-io__conan-20032baseliner2failed3536K1.18M15K199K828s$0.036
conan-io__conan-20078baseliner1resolved6360K3.45M33K505K448s$0.079
conan-io__conan-20078baseliner2resolved9468K6.56M57K895K1197s$0.128
conan-io__conan-20136baseliner1failed9668K7.36M74K1.03M760s$0.153
conan-io__conan-20136baseliner2resolved6257K3.49M42K533K448s$0.089
conan-io__conan-20146baseliner1resolved4235K1.49M15K229K537s$0.038
conan-io__conan-20146baseliner2resolved3628K1.08M15K181K270s$0.033
conan-io__conan-20208baseliner1failed6639K3.44M48K526K498s$0.090
conan-io__conan-20208baseliner2failed3323K939K20K176K284s$0.036
conan-io__conan-20217baseliner1resolved2931K1.07M17K190K228s$0.036
conan-io__conan-20217baseliner2resolved4031K1.27M12K195K185s$0.032
dask__dask-12301baseliner1failed9961K6.52M60K893K1449s$0.129
dask__dask-12301baseliner2resolved11564K7.85M61K1.03M1457s$0.140
dask__dask-12430baseliner1failed5431K1.60M29K277K658s$0.053
dask__dask-12430baseliner2failed7034K2.91M44K459K1888s$0.081
falconry__falcon-2673baseliner1failed6651K3.65M45K551K423s$0.091
falconry__falcon-2673baseliner2failed11293K7.06M97K1.09M825s$0.186
falconry__falcon-2682baseliner1resolved4377K1.58M17K285K353s$0.053
falconry__falcon-2682baseliner2resolved5741K2.67M32K404K333s$0.067
getmoto__moto-10007baseliner1resolved3054K725K8K150K231s$0.030
getmoto__moto-10007baseliner2resolved2520K541K6K93K166s$0.017
getmoto__moto-10012baseliner1resolved2927K888K10K146K787s$0.025
getmoto__moto-10012baseliner2resolved3732K1.33M15K209K806s$0.035
getmoto__moto-10028baseliner1resolved16484K11.75M61K1.44M1677s$0.168
getmoto__moto-10028baseliner2failed9959K6.84M59K921K1686s$0.130
getmoto__moto-10041baseliner1resolved4224K1.05M12K163K952s$0.027
getmoto__moto-10041baseliner2resolved3724K945K8K143K222s$0.023
getmoto__moto-10057baseliner1failed5236K1.95M18K286K764s$0.044
getmoto__moto-10057baseliner2resolved4126K1.12M13K176K247s$0.030
getmoto__moto-10067baseliner1resolved2530K737K9K130K268s$0.024
getmoto__moto-10067baseliner2resolved3835K1.31M17K217K258s$0.039
getmoto__moto-10070baseliner1failed4236K1.54M25K266K346s$0.050
getmoto__moto-10070baseliner2failed6092K6.00M69K899K402s$0.146
getmoto__moto-10093baseliner1resolved4443K1.87M16K278K367s$0.044
getmoto__moto-10093baseliner2resolved4441K1.97M20K299K304s$0.048
getmoto__moto-10117baseliner1resolved4031K1.33M15K208K265s$0.035
getmoto__moto-10117baseliner2resolved3759K2.37M33K393K707s$0.071
getmoto__moto-10127baseliner1resolved3634K1.21M14K196K249s$0.034
getmoto__moto-10127baseliner2resolved2528K704K8K123K128s$0.022
getmoto__moto-10146baseliner1resolved1013K162K3K38K145s$0.008
getmoto__moto-10146baseliner2resolved3928K1.24M20K212K217s$0.040
getmoto__moto-10170baseliner1resolved1717K368K8K77K342s$0.017
getmoto__moto-10170baseliner2resolved2317K460K7K84K168s$0.016
jd__tenacity-606baseliner1resolved2023K462K9K96K154s$0.021
jd__tenacity-606baseliner2resolved6461K3.64M43K554K1251s$0.092
jd__tenacity-615baseliner1resolved6342K3.05M35K450K324s$0.072
jd__tenacity-615baseliner2resolved6337K2.80M33K416K293s$0.068
jd__tenacity-640baseliner1resolved4135K1.64M21K263K239s$0.046
jd__tenacity-640baseliner2resolved5031K1.70M15K246K208s$0.038
jd__tenacity-653baseliner1failed4832K1.38M21K234K453s$0.044
jd__tenacity-653baseliner2failed5834K2.14M41K371K679s$0.072
keephq__keep-6611baseliner1resolved4234K1.21M12K190K484s$0.032
keephq__keep-6611baseliner2resolved9152K4.58M31K604K612s$0.081
keephq__keep-6638baseliner1resolved3227K866K10K145K359s$0.026
keephq__keep-6638baseliner2resolved4831K1.44M13K216K346s$0.034
livekit__agents-6625baseliner1failed2527K638K8K115K303s$0.022
livekit__agents-6625baseliner2failed3323K1.09M16K181K261s$0.033
mvt-project__mvt-815baseliner1resolved3237K1.02M9K166K202s$0.028
mvt-project__mvt-815baseliner2failed414K35K83720K59s$0.005
nltk__nltk-3580baseliner1failed8254K3.91M42K572K533s$0.090
nltk__nltk-3580baseliner2failed6131K2.00M28K315K566s$0.055
sktime__sktime-10583baseliner1failed5733K1.83M33K314K962s$0.060
sktime__sktime-10583baseliner2failed4727K1.54M44K312K1063s$0.070
vega__altair-4019baseliner1failed4425K1.14M18K193K1538s$0.036
vega__altair-4019baseliner2failed6633K2.29M28K344K1949s$0.057