reconbench

Indexsquoosh-image-compressionrun

codex/gpt-5.6-sol

20260830T163630Z-5d6110

completedtrusted

Verdict

Overall91.0
Score arithmetic
ComponentValueWeightContribution
Submission + build gatesubmission contract + install + build; policy is gated below✓ passedgate—
Global visual0.8209× 0.50+0.4104
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= 0.9104

Visual evidence

Fig. 01desktopbase target · 1440×900

visual 78.5
reference capture for desktop
reference
candidate capture for desktop
candidate

pixel 94.8thumbnail 96.5fg-IoU 96.9edge 25.2dimension 100.0

Fig. 02mobilebase target · 390×844

visual 71.5
reference capture for mobile
reference
candidate capture for mobile
candidate

pixel 91.8thumbnail 92.9fg-IoU 38.2edge 84.7dimension 100.0

Fig. 03desktopbase target · 1440×900

visual 96.6
reference capture for desktop
reference
candidate capture for desktop
candidate

pixel 98.3thumbnail 98.6fg-IoU 100.0edge 88.9dimension 100.0

Fig. 04desktopbase target · 1440×900

visual 96.7
reference capture for desktop
reference
candidate capture for desktop
candidate

pixel 98.2thumbnail 98.6fg-IoU 100.0edge 89.3dimension 100.0

Fig. 05mobilebase target · 390×844

visual 96.5
reference capture for mobile
reference
candidate capture for mobile
candidate

pixel 98.1thumbnail 98.6fg-IoU 99.9edge 88.6dimension 100.0

Workflow replay

6 / 6 passed · weight 3.0 / 3.0

ResultCheckKindDimensionWeightDetail
image-compression-desktop.upload-source—workflow1.0—
image-compression-desktop.loaded-editor—workflow0.1—
image-compression-desktop.quality-50—workflow0.8—
image-compression-desktop.quality-result—workflow0.1—
image-compression-mobile.upload-source-mobile—workflow0.9—
image-compression-mobile.mobile-loaded—workflow0.1—

Deterministic checks

6 / 6 passed · weight 3.0 / 3.0

ResultCheckKindDimensionWeightDetail
required-file:submission.json—gate0.0—
source-upload-desktopselectorfunctional0.5—
source-upload-mobileselectorfunctional0.5—
squoosh-homeselectorfunctional0.5—
mobile-no-overflowno_horizontal_overflowresponsive1.0—
mobile-samplesselectorresponsive0.5—
Apparatus · agent, timing, usage and digests

Agent

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

Variant & network

Variant
requested-recovery-after-build-failure
Network policy
deny
Enforced
true

Timing & usage

Started
2026-08-30 16:36:31 UTC
Finished
2026-08-30 16:47:33 UTC
Elapsed
11m 02s
Input tokens
2.23M
Output tokens
29.1k
Cost
—

Content digests

evaluator_environment
fb0d05b65ef3dfe67d61dcd60b2a259135f2dae2641843e5543c1fa04be46e9c
grader
6c4737b6bfdf1979112b778e497c56783dfe12bf85502aed630d8d7c545871b2
oracle
31eaf13c43733562d1d44a6ae41d65d7adb925e41ebd23416e5632e6eb7701dc
runtime_config
8e1e8a0364b8fb50feb0efbf92db64dd784927350e9bb88927dd2c2f98631b40
submission
6f71c6baa9613da9479a91f6359b846d90337988e9b17c1eb721a4332c33b826
task
eaa2e0896d8ea8b86948a5bcf9e258df064ab9bab43c2d2631455329298d24f0

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.