reconbench

Indexcyberchef-base64-workbenchrun

cc/opus

20260830T152150Z-27d7f9

completedtrusted

Verdict

Overall98.3
Score arithmetic
ComponentValueWeightContribution
Submission + build gatesubmission contract + install + build; policy is gated below✓ passedgate—
Global visual0.9670× 0.50+0.4835
Weighted regions1.0000× 0.00+0.0000
Functional1.0000× 0.10+0.1000
Responsive1.0000× 0.10+0.1000
Workflow1.0000× 0.30+0.3000
Preservation1.0000× 0.00+0.0000
Policy1.0000gate—
Overall= 0.9835

Visual evidence

Fig. 01desktopbase target · 1440×900

visual 98.8
reference capture for desktop
reference
candidate capture for desktop
candidate

pixel 99.6thumbnail 99.9fg-IoU 98.3edge 98.1dimension 100.0

Fig. 02mobilebase target · 390×1658

visual 98.4
reference capture for mobile
reference
candidate capture for mobile
candidate

pixel 99.3thumbnail 99.6fg-IoU 97.7edge 97.6dimension 100.0

Fig. 03desktopbase target · 1440×900

visual 98.8
reference capture for desktop
reference
candidate capture for desktop
candidate

pixel 99.4thumbnail 99.8fg-IoU 98.6edge 97.9dimension 100.0

Workflow replay

4 / 4 passed · weight 2.0 / 2.0

ResultCheckKindDimensionWeightDetail
base64-recipe.initial-empty—workflow0.3—
base64-recipe.add-operation—workflow0.7—
base64-recipe.enter-input—workflow0.9—
base64-recipe.base64-result—workflow0.1—

Deterministic checks

6 / 6 passed · weight 3.0 / 3.0

ResultCheckKindDimensionWeightDetail
required-file:submission.json—gate0.0—
operation-presentselectorfunctional0.5—
recipe-presentselectorfunctional0.5—
input-presentselectorfunctional0.5—
output-presentselectorfunctional0.5—
mobile-no-overflowno_horizontal_overflowresponsive1.0—
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 15:21:50 UTC
Finished
2026-08-30 15:58:12 UTC
Elapsed
36m 22s
Input tokens
210
Output tokens
152.7k
Cost
$12.80

Content digests

evaluator_environment
fb0d05b65ef3dfe67d61dcd60b2a259135f2dae2641843e5543c1fa04be46e9c
grader
6c4737b6bfdf1979112b778e497c56783dfe12bf85502aed630d8d7c545871b2
oracle
16d57d6bbfad8e0b82634edb74378733037e081febd149931e3584fdcabc0d3e
runtime_config
07799f9e8ffde0087bbe740535c7d232574d2feb1f9b90a1a9171a6cf68bf5e3
submission
cdc3407a9072ea956f187f18b6178aefb989ed5ddd3937118bc2b07d2d064e3b
task
389441dd2105fe0d6c16c27630169d258a18314c42a4e191ecb1f97e751be3af

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.