reconbench

Indexcyberchef-base64-workbenchrun

codex/gpt-5.6-luna

20260830T064045Z-ac0488

completedtrusted

Verdict

Overall20.7
Score arithmetic
ComponentValueWeightContribution
Submission + build gatesubmission contract + install + build; policy is gated below✓ passedgate—
Global visual0.0148× 0.50+0.0074
Weighted regions1.0000× 0.00+0.0000
Functional1.0000× 0.10+0.1000
Responsive1.0000× 0.10+0.1000
Workflow0.0000× 0.30+0.0000
Preservation1.0000× 0.00+0.0000
Policy1.0000gate—
Overall= 0.2074

Visual evidence

Fig. 01desktopbase target · 1440×900

visual 92.3
reference capture for desktop
reference
candidate capture for desktop
candidate

pixel 98.9thumbnail 99.3fg-IoU 94.1edge 78.8dimension 100.0

Fig. 02mobilebase target · 390×1658

visual 89.5
reference capture for mobile
reference
candidate capture for mobile
candidate

pixel 98.0thumbnail 98.6fg-IoU 85.5edge 82.2dimension 99.7

Fig. 03desktopbase target · 1440×900

visual 0.0

Checkpoint not reached — the candidate build never produced this state, so it scores zero and there is no capture to compare.

Declared workflow checkpoint was not reached

reference capture for desktop
reference
no capture
candidate

pixel —thumbnail —fg-IoU —edge —dimension —

Workflow replay

0 / 4 passed · weight 0.0 / 2.0

ResultCheckKindDimensionWeightDetail
base64-recipe.initial-empty—workflow0.3Expected text '', got 'Recipe\n⌃\n▣\n▰\n▣\nSTEP\n👨\u200d🍳 BAKE!\n✓\nAuto Bake'; Expected text '', got 'Output\n▣\n▢\n⇧\n⛶\nABC\u30000\u3000 ☷\u30001\n◷\u30000msTT Raw Bytes\u3000 ↵ LF'
base64-recipe.add-operation—workflow0.7Skipped after prior workflow failure
base64-recipe.enter-input—workflow0.9Skipped after prior workflow failure
base64-recipe.base64-result—workflow0.1Skipped after prior workflow failure

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
codex/gpt-5.6-luna
Runtime
codex · Docker version 29.2.1, build a5c7197
Model
gpt-5.6-luna
Effort
high
Tool profile
baseline

Variant & network

Variant
—
Network policy
deny
Enforced
true

Timing & usage

Started
2026-08-30 06:40:46 UTC
Finished
2026-08-30 06:48:13 UTC
Elapsed
7m 26s
Input tokens
1.03M
Output tokens
21.3k
Cost
—

Content digests

evaluator_environment
564a05bc7ac8026fa368ab9146880aff42fcc4ecb8ba57deec14467857a95f9c
grader
80a401f799a26ee91f913cf5bf5ce3509e570cb6fc060c78b5941a86f860b3cd
oracle
16d57d6bbfad8e0b82634edb74378733037e081febd149931e3584fdcabc0d3e
runtime_config
9be2f291cf148821361bf9e22eb4aa3f6d242f4063f2860b53f9031f62c8baed
submission
963d5002ef78660f93127d8366675d6fe7a764bae5caa6a129e26b39615a839a
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.