E3 · LED wording: branch exp/led-wording (codes.md says led_output_low names the effect whatever the cause). Provider-error attempts are left out. Not part of the headline.

optobench runs

18 trials · total cost $31.59 · not on this page: 3 attempts that ended on provider rate limits ($0.32, re-run in exp_led_wording_openai); they are in the dataset's episodes table · 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
argont4_takeover3—32 / 30.983$8.4903$2.8301
astrat4_takeover3—31 / 30.99$10.3995$3.4665
opust4_takeover3—32 / 30.99$6.3211$2.1070
solt4_takeover3—32 / 30.667$1.3720$0.4573
sonnett4_takeover3—31 / 30.983$4.3463$1.4488
terrat4_takeover3—30 / 30.333$0.6638$0.2213

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

headlineargont4_takeovert_present_faultstrial 0submitted1pass$3.15722152
headlineargont4_takeovert_present_faultstrial 1submitted1pass$2.93472661
headlineargont4_takeovert_present_faultstrial 2submitted0.949fail$2.39841985
headlineastrat4_takeovert_present_faultstrial 0submitted0.971fail$3.77743759
headlineastrat4_takeovert_present_faultstrial 1submitted0.998fail$3.98673968
headlineastrat4_takeovert_present_faultstrial 2submitted1pass$2.63543249
headlineopust4_takeovert_present_faultstrial 0submitted0.971fail$2.12221766
headlineopust4_takeovert_present_faultstrial 1submitted1pass$2.03191660
headlineopust4_takeovert_present_faultstrial 2submitted1pass$2.16702368
headlinesolt4_takeovert_present_faultstrial 0submitted1pass$0.45823258
headlinesolt4_takeovert_present_faultstrial 1submitted1pass$0.46503057
headlinesolt4_takeovert_present_faultstrial 2submitted0fail$0.44883861
headlinesonnett4_takeovert_present_faultstrial 0submitted0.968fail$1.59413575
headlinesonnett4_takeovert_present_faultstrial 1submitted1pass$1.47313384
headlinesonnett4_takeovert_present_faultstrial 2submitted0.981fail$1.27912870
headlineterrat4_takeovert_present_faultstrial 0submitted0fail$0.16111635
headlineterrat4_takeovert_present_faultstrial 1submitted0.998fail$0.25334268
headlineterrat4_takeovert_present_faultstrial 2submitted0fail$0.24943057