sheetparser
eval runs
jobs
playground
tools
loops
Eval runs
Refresh
loading…
run
quality
mean NED
median NED
exact
episodes
model
split
started
loop
Samples
— worst first; click a column to re-sort
loading…
sample
omr_ned
exact
emitted
compiles
duration
tool calls
error
Ground truth vs parsed
Measure diff
Tool history
Confidence by measure
Downloads