cc/opus

20260830T143625Z-0146d7

completedtrusted

Verdict

Overall93.1

Score arithmetic
Component	Value	Weight	Contribution
Submission + build gatesubmission contract + install + build; policy is gated below	✓ passed	gate	—
Global visual	0.8619	× 0.50	+0.4310
Weighted regions	1.0000	× 0.00	+0.0000
Functional	1.0000	× 0.10	+0.1000
Responsive	1.0000	× 0.10	+0.1000
Workflow	1.0000	× 0.30	+0.3000
Preservation	1.0000	× 0.00	+0.0000
Policy	1.0000	gate	—
Overall			= 0.9310

Visual evidence

Fig. 01desktopbase target · 1440×900

visual 96.1

reference capture for desktop — reference

candidate capture for desktop — candidate

pixel 98.6thumbnail 99.5fg-IoU 93.9edge 94.3dimension 100.0

Fig. 02mobilebase target · 390×844

visual 92.6

reference capture for mobile — reference

candidate capture for mobile — candidate

pixel 97.6thumbnail 98.3fg-IoU 87.3edge 91.4dimension 100.0

Fig. 03mobile-readerstate on mobile

visual 94.7

reference capture for mobile-reader — reference

candidate capture for mobile-reader — candidate

pixel 98.0thumbnail 98.6fg-IoU 92.1edge 92.6dimension 100.0

Fig. 04desktopbase target · 1440×900

visual 95.8

pixel 99.4thumbnail 99.7fg-IoU 93.1edge 93.6dimension 100.0

Workflow replay

5 / 5 passed · weight 2.0 / 2.0

Check	Kind	Dimension	Weight	Detail
edit-persistence.replace-note	—	workflow	0.6	—
edit-persistence.replace-title	—	workflow	0.4	—
edit-persistence.reload	—	workflow	0.8	—
edit-persistence.restore-title	—	workflow	0.1	—
edit-persistence.persisted	—	workflow	0.1	—

Deterministic checks

7 / 7 passed · weight 4.5 / 4.5

Check	Kind	Dimension	Weight	Detail
required-file:submission.json	—	gate	0.0	—
seeded-preview	text	functional	1.0	—
editor-present	selector	functional	0.5	—
reader-control	selector	functional	0.5	—
document-title	selector	functional	0.5	—
mobile-no-overflow	no_horizontal_overflow	responsive	1.0	—
mobile-preview-hidden	hidden	responsive	1.0	—

Apparatus · agent, timing, usage and digests

Agent

Selector: cc/opus
Runtime: claude_code · Docker version 29.2.1, build a5c7197
Model: claude-opus-5
Effort: high
Tool profile: baseline

Variant & network

Variant: —
Network policy: deny
Enforced: true

Timing & usage

Started: 2026-08-30 14:36:26 UTC
Finished: 2026-08-30 15:13:51 UTC
Elapsed: 37m 25s
Input tokens: 242
Output tokens: 167.7k
Cost: $14.80

Content digests

evaluator_environment: fb0d05b65ef3dfe67d61dcd60b2a259135f2dae2641843e5543c1fa04be46e9c
grader: 6c4737b6bfdf1979112b778e497c56783dfe12bf85502aed630d8d7c545871b2
oracle: b65c5852c9f91526271059dff43b1bcbdc3096516912e18bd93152a0cdafd081
runtime_config: 07799f9e8ffde0087bbe740535c7d232574d2feb1f9b90a1a9171a6cf68bf5e3
submission: 9e83444d522134d903df77d3f855d0a4cb853bee286320a7ed206429e6de6344
task: 5a9a10ac23a51761eb1c771a22309ac235f4f86aeb670a7a131198606f30c223

Digests pin the exact task package, submission tree, oracle, grader and evaluator environment used. They are how a result is re-verified without trusting this page.

Trace summary

trace summarizedclaude-code-jsonl-v1

Derived trace statistics
events	1,290
tool calls	138
commands	78
file edits	29
wall clock	37m 25s
input tokens	242
output tokens	167.7k

Tool activity profile

Derived action counts; bars are normalized to the largest count.

commands78

file edits29

Categories may overlap. Counts describe activity shape, not task quality or research effort.