run · run_zirrnltio3dv86yi · filed 2026-08-07 16:18:31
Share

pdf-mixed-scan-docling-ocr

Grader output

free-form JSON · this task's own
0.900grader.score18 of 20 cases passed
score
0.900
passed
total cases
20
passed cases
18
skipped cases
0
pass threshold
0.800
cost total
$0.677
latency p95
475.44 s
latency total
602.00 s
latency median
5.73 s

score by category

locate
67%
compare
100%
compute
100%
reconcile
100%
reconstruct
100%
cross_reference
83%

extras

n_scored=20n_skipped_no_gold=0

Fields here are the task author's — trap neither interprets nor validates them.

Run frame

written by trap · always present
cases
20
duration total
602.00s
cost
$0.677
engine
claude-sonnet-5

environment · self-reported, not validated

os
macOS 14.0
arch
arm64
kernel
Darwin 23.0.0
cpu
Apple M1 · 8 cores
memory
8.0 GB
trap
0.0.14
per-case results · all 20, in case_id order
discuss this task →