Development history: earlier code, development history, not scored. Same-named trials from different checks carry -2, -3 ids; each page's footer names its source folder. Not part of the headline.

optobench runs

218 trials · 27 harness failures (no score) · total cost $42.61 · 14 more development records ($2.23: 10 Nemotron T1 sweep runs and 4 aborted checks) are in the dataset's episodes table only · click a trial to step through it

By agent and task (trials shown by the filters)

agent task trialsharness errors submitted all passmean end score costcost / trial
deepseekt1_connectivity4—30 / 40.59$0.3543$0.0886
deepseekt2_setup4—40 / 40.954$0.2239$0.0560
deepseekt3_light4—30 / 40.26$0.3096$0.0774
deepseekt4_takeover4—20 / 40.224$0.3341$0.0835
deepseekt5_traces4—32 / 40.736$0.3856$0.0964
deepseekall tasks20—152 / 200.553$1.6075$0.0804
flasht1_connectivity4—42 / 40.948$3.8548$0.9637
flasht2_setup4—41 / 40.967$1.6205$0.4051
flasht3_light4—40 / 40.333$4.9567$1.2392
flasht4_takeover4—40 / 40.88$2.4937$0.6234
flasht5_traces4—41 / 40.96$6.0645$1.5161
flashall tasks20—204 / 200.818$18.9902$0.9495
haikut1_connectivity10641 / 40.724$0.4692$0.0469
haikut2_setup10640 / 40.846$0.1368$0.0137
haikut3_light10641 / 40.709$0.4444$0.0444
haikut4_takeover10640 / 40.718$0.6441$0.0644
haikut5_traces8351 / 50.923$0.3037$0.0380
haikuall tasks4827213 / 210.79$1.9982$0.0416
lunat1_connectivity4—40 / 40.438$0.2709$0.0677
lunat2_setup5—51 / 50.84$0.0715$0.0143
lunat3_light4—40 / 40.453$0.2119$0.0530
lunat4_takeover4—40 / 40.178$0.2703$0.0676
lunat5_traces5—50 / 50.931$0.0961$0.0192
lunaall tasks22—221 / 220.597$0.9207$0.0418
nemotront1_connectivity54—480 / 540.453$7.7823$0.1441
nemotront2_setup17—152 / 170.751$2.3810$0.1401
nemotront3_light15—152 / 150.498$3.7108$0.2474
nemotront4_takeover12—120 / 120.385$2.5281$0.2107
nemotront5_traces10—80 / 100.709$2.6932$0.2693
nemotronall tasks108—984 / 1080.522$19.0953$0.1768

Each trial has one end grade, computed once after the run ends. Harness failures (the run stopped on a provider or harness error) are listed but have no score: they are left out of "all pass" and the means.

Trials

headlinedeepseekt1_connectivitystale_framestrial 0no submission0fail$0.05491324
headlinedeepseekt1_connectivitystale_framestrial 0submitted0.957fail$0.095844115
headlinedeepseekt1_connectivitytrigger_cabletrial 0submitted0.646fail$0.10624294
headlinedeepseekt1_connectivityusb_loosetrial 0submitted0.758fail$0.09753491
headlineflasht1_connectivitystale_framestrial 0submitted1pass$1.26793098
headlineflasht1_connectivitystale_framestrial 0submitted0.957fail$0.76332679
headlineflasht1_connectivitytrigger_cabletrial 0submitted1pass$0.81582881
headlineflasht1_connectivityusb_loosetrial 0submitted0.837fail$1.00782991
headlinehaikut1_connectivitystale_framestrial 0harness errorno score—$0.000001
headlinehaikut1_connectivitystale_framestrial 0harness errorno score—$0.000001
headlinehaikut1_connectivitystale_framestrial 0submitted1pass$0.13934698
headlinehaikut1_connectivitystale_framestrial 0submitted0.957fail$0.09103278
headlinehaikut1_connectivitytrigger_cabletrial 0harness errorno score—$0.000001
headlinehaikut1_connectivitytrigger_cabletrial 0harness errorno score—$0.000001
headlinehaikut1_connectivitytrigger_cabletrial 0submitted0.939fail$0.174456110
headlinehaikut1_connectivityusb_loosetrial 0harness errorno score—$0.000001
headlinehaikut1_connectivityusb_loosetrial 0harness errorno score—$0.000001
headlinehaikut1_connectivityusb_loosetrial 0submitted0fail$0.06442050
headlinelunat1_connectivitystale_framestrial 0submitted0.927fail$0.09644994
headlinelunat1_connectivitystale_framestrial 0submitted0fail$0.06993869
headlinelunat1_connectivitytrigger_cabletrial 0submitted0.826fail$0.05223457
headlinelunat1_connectivityusb_loosetrial 0submitted0fail$0.05254366
headlinenemotront1_connectivitydead_culturetrial 0submitted0.256fail$0.258861102
headlinenemotront1_connectivitydead_culturetrial 0submitted0.644fail$0.25734591
headlinenemotront1_connectivitydead_culturetrial 0submitted0.059fail$0.13962852
headlinenemotront1_connectivitydead_culturetrial 1submitted0.887fail$0.18344368
headlinenemotront1_connectivitydead_culturetrial 2no submission0fail$0.17286095
headlinenemotront1_connectivityhdmi_loosetrial 0submitted0.868fail$0.10642751
headlinenemotront1_connectivityhdmi_loosetrial 0submitted0.847fail$0.11482951
headlinenemotront1_connectivityhdmi_loosetrial 0submitted0.906fail$0.09723248
headlinenemotront1_connectivityhdmi_loosetrial 1submitted0.905fail$0.10482643
headlinenemotront1_connectivityhdmi_loosetrial 2submitted0.41fail$0.19686191
headlinenemotront1_connectivityloose_wiretrial 0submitted0.743fail$0.13934281
headlinenemotront1_connectivityloose_wiretrial 0no submission0fail$0.16686098
headlinenemotront1_connectivityloose_wiretrial 1submitted0.606fail$0.13683566
headlinenemotront1_connectivityloose_wiretrial 2submitted0.548fail$0.21003469
headlinenemotront1_connectivitylow_disktrial 0submitted0.755fail$0.10173053
headlinenemotront1_connectivitylow_disktrial 0submitted0.944fail$0.08572437
headlinenemotront1_connectivitylow_disktrial 1submitted0.732fail$0.12814165
headlinenemotront1_connectivitylow_disktrial 2submitted0.71fail$0.11304064
headlinenemotront1_connectivitymask_fliptrial 0submitted0fail$0.20074487
headlinenemotront1_connectivitymask_fliptrial 0no submission0fail$0.15376087
headlinenemotront1_connectivitymask_fliptrial 1submitted0.077fail$0.12911843
headlinenemotront1_connectivitymask_fliptrial 2submitted0.187fail$0.17914885
headlinenemotront1_connectivitynonetrial 0submitted0.724fail$0.08533250
headlinenemotront1_connectivitynonetrial 0submitted0.415fail$0.11403257
headlinenemotront1_connectivitynonetrial 0submitted0.67fail$0.11243256
headlinenemotront1_connectivitynonetrial 0submitted0.731fail$0.08452549
headlinenemotront1_connectivitynonetrial 1submitted0.672fail$0.09692950
headlinenemotront1_connectivitynonetrial 1submitted0.862fail$0.09062042
headlinenemotront1_connectivitynonetrial 2submitted0.656fail$0.10353959
headlinenemotront1_connectivityoperator_awaytrial 0submitted0.86fail$0.13563055
headlinenemotront1_connectivityprojector_standbytrial 0submitted0.919fail$0.10112955
headlinenemotront1_connectivityprojector_standbytrial 0submitted0.518fail$0.13605891
headlinenemotront1_connectivityprojector_standbytrial 1submitted0.641fail$0.09042651
headlinenemotront1_connectivityprojector_standbytrial 2submitted0.724fail$0.11063763
headlinenemotront1_connectivityroom_lighttrial 0submitted0.262fail$0.07322848
headlinenemotront1_connectivityroom_lighttrial 0submitted0.17fail$0.10302648
headlinenemotront1_connectivityroom_lighttrial 1submitted0.224fail$0.08693252
headlinenemotront1_connectivityroom_lighttrial 2submitted0.306fail$0.08032038
headlinenemotront1_connectivitystale_framestrial 0submitted0.753fail$0.13643771
headlinenemotront1_connectivitystale_framestrial 0submitted0.059fail$0.18264793
headlinenemotront1_connectivitystale_framestrial 0no submission0fail$0.22826093
headlinenemotront1_connectivitystale_framestrial 0submitted0fail$0.12383268
headlinenemotront1_connectivitystale_framestrial 0submitted0fail$0.14213867
headlinenemotront1_connectivitystale_framestrial 1submitted0.887fail$0.11302950
headlinenemotront1_connectivitystale_framestrial 2submitted0.742fail$0.16035084
headlinenemotront1_connectivitytrigger_cabletrial 0no submission0fail$0.16116093
headlinenemotront1_connectivitytrigger_cabletrial 0submitted0fail$0.20944377
headlinenemotront1_connectivitytrigger_cabletrial 0submitted0.599fail$0.17735798
headlinenemotront1_connectivitytrigger_cabletrial 0submitted0fail$0.16303558
headlinenemotront1_connectivitytrigger_cabletrial 1submitted0.647fail$0.15865190
headlinenemotront1_connectivitytrigger_cabletrial 1submitted0.183fail$0.14296187
headlinenemotront1_connectivitytrigger_cabletrial 2submitted0.162fail$0.18972755
headlinenemotront1_connectivityusb_loosetrial 0no submission0fail$0.303660118
headlinenemotront1_connectivityusb_loosetrial 0submitted0fail$0.20974385
headlinedeepseekt2_setupdistortion_densetrial 0submitted0.973fail$0.03922157
headlinedeepseekt2_setupflip_staletrial 0submitted0.956fail$0.11391749
headlinedeepseekt2_setupflip_staletrial 0submitted0.933fail$0.02321635
headlinedeepseekt2_setupmissing_uneventrial 0submitted0.956fail$0.04761554
headlineflasht2_setupdistortion_densetrial 0submitted1pass$0.67192368
headlineflasht2_setupflip_staletrial 0submitted0.956fail$0.32381544
headlineflasht2_setupflip_staletrial 0submitted0.956fail$0.34291743
headlineflasht2_setupmissing_uneventrial 0submitted0.956fail$0.28191536
headlinehaikut2_setupdistortion_densetrial 0harness errorno score—$0.000001
headlinehaikut2_setupdistortion_densetrial 0harness errorno score—$0.000001
headlinehaikut2_setupdistortion_densetrial 0submitted0.984fail$0.03552141
headlinehaikut2_setupflip_staletrial 0harness errorno score—$0.000001
headlinehaikut2_setupflip_staletrial 0harness errorno score—$0.000001
headlinehaikut2_setupflip_staletrial 0submitted0.867fail$0.02741934
headlinehaikut2_setupflip_staletrial 0submitted0.867fail$0.01851830
headlinehaikut2_setupmissing_uneventrial 0harness errorno score—$0.000001
headlinehaikut2_setupmissing_uneventrial 0harness errorno score—$0.000001
headlinehaikut2_setupmissing_uneventrial 0submitted0.667fail$0.05532850
headlinelunat2_setupdistortion_densetrial 0submitted0.867fail$0.01091926
headlinelunat2_setupdistortion_densetrial 0submitted0.867fail$0.01912638
headlinelunat2_setupflip_staletrial 0submitted1pass$0.01411827
headlinelunat2_setupflip_staletrial 0submitted0.867fail$0.00972026
headlinelunat2_setupmissing_uneventrial 0submitted0.598fail$0.01762538
headlinenemotront2_setupcalibration_missingtrial 0no submission0fail$0.407760124
headlinenemotront2_setupcalibration_staletrial 0submitted0.996fail$0.06281529
headlinenemotront2_setupdense_culturetrial 0submitted1pass$0.07881534
headlinenemotront2_setupdistortion_densetrial 0submitted0.742fail$0.01871014
headlinenemotront2_setupfew_markerstrial 0submitted0.667fail$0.332954100
headlinenemotront2_setupflip_staletrial 0submitted0.862fail$0.02411216
headlinenemotront2_setupflip_staletrial 0submitted0.867fail$0.03751422
headlinenemotront2_setuphdmi_loosetrial 0submitted1pass$0.06001729
headlinenemotront2_setuplens_distortiontrial 0submitted0.733fail$0.06251827
headlinenemotront2_setuploose_wiretrial 0submitted0.899fail$0.11563051
headlinenemotront2_setupmask_fliptrial 0submitted0.93fail$0.11642144
headlinenemotront2_setupmissing_uneventrial 0no submission0fail$0.541960151
headlinenemotront2_setupnonetrial 0submitted0.816fail$0.08651627
headlinenemotront2_setupoperator_awaytrial 0submitted0.867fail$0.13543256
headlinenemotront2_setupprojector_standbytrial 0submitted0.733fail$0.10813654
headlinenemotront2_setuproom_lighttrial 0submitted0.828fail$0.10422741
headlinenemotront2_setupuneven_illuminationtrial 0submitted0.832fail$0.08801430
headlinedeepseekt3_lightcluster_fast_bleachtrial 0submitted0.375fail$0.05082555
headlinedeepseekt3_lightconverging_led_lowtrial 0no submission0fail$0.0265817
headlinedeepseekt3_lightconverging_led_lowtrial 0submitted0.667fail$0.099798151
headlinedeepseekt3_lighttwo_targets_room_lighttrial 0submitted0fail$0.132682160
headlineflasht3_lightcluster_fast_bleachtrial 0submitted0.667fail$0.85654086
headlineflasht3_lightconverging_led_lowtrial 0submitted0.667fail$1.130164111
headlineflasht3_lightconverging_led_lowtrial 0submitted0fail$1.124469119
headlineflasht3_lighttwo_targets_room_lighttrial 0submitted0fail$1.845774150
headlinehaikut3_lightcluster_fast_bleachtrial 0harness errorno score—$0.000001
headlinehaikut3_lightcluster_fast_bleachtrial 0harness errorno score—$0.000001
headlinehaikut3_lightcluster_fast_bleachtrial 0submitted0.946pass$0.05792560
headlinehaikut3_lightconverging_led_lowtrial 0harness errorno score—$0.000001
headlinehaikut3_lightconverging_led_lowtrial 0harness errorno score—$0.000001
headlinehaikut3_lightconverging_led_lowtrial 0submitted0.5fail$0.11394795
headlinehaikut3_lightconverging_led_lowtrial 0submitted0.667fail$0.142658118
headlinehaikut3_lighttwo_targets_room_lighttrial 0harness errorno score—$0.000001
headlinehaikut3_lighttwo_targets_room_lighttrial 0harness errorno score—$0.000001
headlinehaikut3_lighttwo_targets_room_lighttrial 0submitted0.725fail$0.12994396
headlinelunat3_lightcluster_fast_bleachtrial 0submitted0.48fail$0.04635581
headlinelunat3_lightconverging_led_lowtrial 0submitted0.667fail$0.090357119
headlinelunat3_lightconverging_led_lowtrial 0submitted0.667fail$0.03644166
headlinelunat3_lighttwo_targets_room_lighttrial 0submitted0fail$0.03903878
headlinenemotront3_lightclose_neighbourstrial 0submitted0.617fail$0.212282106
headlinenemotront3_lightcluster_fast_bleachtrial 0submitted0.375fail$0.17293865
headlinenemotront3_lightconvergingtrial 0submitted0.617fail$0.31066799
headlinenemotront3_lightconverging_led_lowtrial 0submitted0fail$0.261159111
headlinenemotront3_lightconverging_led_lowtrial 0submitted0fail$0.17886285
headlinenemotront3_lightdead_culturetrial 0submitted0.35fail$0.21046084
headlinenemotront3_lightfast_bleachtrial 0submitted0.35fail$0.17334667
headlinenemotront3_lightled_lowtrial 0submitted0.77fail$0.33465989
headlinenemotront3_lightloose_wiretrial 0submitted0.97pass$0.19175077
headlinenemotront3_lightnonetrial 0submitted0.68fail$0.19494770
headlinenemotront3_lightroom_lighttrial 0submitted0.45fail$0.19565173
headlinenemotront3_lightstale_framestrial 0submitted0.667fail$0.33706191
headlinenemotront3_lightstrong_crosstalktrial 0submitted0.958pass$0.338646105
headlinenemotront3_lightstrong_inputtrial 0submitted0.667fail$0.394661107
headlinenemotront3_lighttwo_targets_room_lighttrial 0submitted0fail$0.20455796
headlinedeepseekt4_takeovert_dead_jumpertrial 0no submission0fail$0.0367012
headlinedeepseekt4_takeovert_dead_jumpertrial 0no submission0fail$0.0584625
headlinedeepseekt4_takeovert_flip_disktrial 0submitted0fail$0.118733119
headlinedeepseekt4_takeovert_present_faultstrial 0submitted0.897fail$0.120445131
headlineflasht4_takeovert_dead_jumpertrial 0submitted0.946fail$0.95741178
headlineflasht4_takeovert_dead_jumpertrial 0submitted0.924fail$0.64001458
headlineflasht4_takeovert_flip_disktrial 0submitted0.81fail$0.4783143
headlineflasht4_takeovert_present_faultstrial 0submitted0.841fail$0.4181143
headlinehaikut4_takeovert_dead_jumpertrial 0harness errorno score—$0.000001
headlinehaikut4_takeovert_dead_jumpertrial 0harness errorno score—$0.000001
headlinehaikut4_takeovert_dead_jumpertrial 0submitted0.973fail$0.15993488
headlinehaikut4_takeovert_dead_jumpertrial 0submitted0.981fail$0.14163279
headlinehaikut4_takeovert_flip_disktrial 0harness errorno score—$0.000001
headlinehaikut4_takeovert_flip_disktrial 0harness errorno score—$0.000001
headlinehaikut4_takeovert_flip_disktrial 0submitted0fail$0.164953112
headlinehaikut4_takeovert_present_faultstrial 0harness errorno score—$0.000001
headlinehaikut4_takeovert_present_faultstrial 0harness errorno score—$0.000001
headlinehaikut4_takeovert_present_faultstrial 0submitted0.917fail$0.177746106
headlinelunat4_takeovert_dead_jumpertrial 0submitted0.315fail$0.08362864
headlinelunat4_takeovert_dead_jumpertrial 0submitted0fail$0.07102253
headlinelunat4_takeovert_flip_disktrial 0submitted0.395fail$0.04541842
headlinelunat4_takeovert_present_faultstrial 0submitted0fail$0.07032158
headlinenemotront4_takeovercleantrial 0submitted0.872fail$0.12801635
headlinenemotront4_takeoverdead_culture_swaptrial 0submitted0.028fail$0.21752756
headlinenemotront4_takeoverdisk_note_finetrial 0submitted0.61fail$0.20281833
headlinenemotront4_takeoverdisk_triagetrial 0submitted0.768fail$0.1399832
headlinenemotront4_takeoverflip_grid_checktrial 0submitted0fail$0.18504177
headlinenemotront4_takeoverfrozen_counterstrial 0submitted0.925fail$0.23562273
headlinenemotront4_takeoverloose_jumpertrial 0submitted0.597fail$0.34344594
headlinenemotront4_takeovermoved_sampletrial 0submitted0.822fail$0.22482664
headlinenemotront4_takeovert_dead_jumpertrial 0submitted0fail$0.24472570
headlinenemotront4_takeovert_dead_jumpertrial 0submitted0fail$0.18832356
headlinenemotront4_takeovert_flip_disktrial 0submitted0fail$0.15191240
headlinenemotront4_takeovert_present_faultstrial 0submitted0fail$0.26633787
headlinedeepseekt5_tracesbleached_and_droppedtrial 0submitted0.993pass$0.11761112
headlinedeepseekt5_traceseverythingtrial 0submitted0.993pass$0.11211126
headlinedeepseekt5_tracesfrozen_and_off_targettrial 0no submission0fail$0.0769042
headlinedeepseekt5_tracesfrozen_and_off_targettrial 0submitted0.959fail$0.0789175
headlineflasht5_tracesbleached_and_droppedtrial 0submitted0.986pass$1.30811103
headlineflasht5_traceseverythingtrial 0submitted0.978fail$1.53601120
headlineflasht5_tracesfrozen_and_off_targettrial 0submitted0.909fail$2.18861152
headlineflasht5_tracesfrozen_and_off_targettrial 0submitted0.968fail$1.0318180
headlinehaikut5_tracesbleached_and_droppedtrial 0harness errorno score—$0.000001
headlinehaikut5_tracesbleached_and_droppedtrial 0submitted0.886fail$0.0766148
headlinehaikut5_traceseverythingtrial 0harness errorno score—$0.000001
headlinehaikut5_traceseverythingtrial 0submitted0.967fail$0.0785141
headlinehaikut5_traceseverythingtrial 0submitted0.95fail$0.0573141
headlinehaikut5_tracesfrozen_and_off_targettrial 0harness errorno score—$0.000001
headlinehaikut5_tracesfrozen_and_off_targettrial 0submitted0.985pass$0.0440137
headlinehaikut5_tracesfrozen_and_off_targettrial 0submitted0.826fail$0.0473141
headlinelunat5_tracesbleached_and_droppedtrial 0submitted0.871fail$0.0190118
headlinelunat5_traceseverythingtrial 0submitted0.968fail$0.0247121
headlinelunat5_traceseverythingtrial 0submitted0.967fail$0.0185114
headlinelunat5_tracesfrozen_and_off_targettrial 0submitted0.972fail$0.0206122
headlinelunat5_tracesfrozen_and_off_targettrial 0submitted0.875fail$0.0133115
headlinenemotront5_tracesbleachedtrial 0submitted0.951fail$0.3361132
headlinenemotront5_tracesbleached_and_droppedtrial 0no submission0fail$0.2244056
headlinenemotront5_tracescleantrial 0submitted0.89fail$0.1728146
headlinenemotront5_tracesdropped_and_lighttrial 0submitted0.829fail$0.3670141
headlinenemotront5_traceseverythingtrial 0submitted0.63fail$0.2779180
headlinenemotront5_traceseverythingtrial 0no submission0fail$0.2559073
headlinenemotront5_tracesfrozen_and_off_targettrial 0submitted0.867fail$0.2207262
headlinenemotront5_tracesfrozen_and_off_targettrial 0submitted0.964fail$0.0646130
headlinenemotront5_tracesfrozen_stretchtrial 0submitted0.98fail$0.4048142
headlinenemotront5_tracesoff_targettrial 0submitted0.984fail$0.3690165