bench
shipshit.dev model benchmark
Leaderboard
Tests
Methodology
Source
v2026.09-smoke
· compare
codex · gpt-5.6-sol · low
vs.
grok · grok-4.6
Post on X
codex · gpt-5.6-sol · low
89.5
$18.45 API-equiv.
partial
grok · grok-4.6
—
— API-equiv.
none
Every task
Issue board filters
68.3
(68.3–68.3, n=1)
run
no screenshot
—
run
shipshit.dev landing hero
92.5
(92.5–92.5, n=1)
run
no screenshot
—
run
Codebase audit, planted defects
no screenshot
79.0
(79.0–79.0, n=1)
run
no screenshot
—
run
Inventory service
no screenshot
—
run
no screenshot
—
run
Shipcut pricing page
100.0
(100.0–100.0, n=1)
run
no screenshot
—
run
Landing page, five themes
100.0
(100.0–100.0, n=1)
run
no screenshot
—
Fix date range overlap bug
no screenshot
100.0
(100.0–100.0, n=1)
run
no screenshot
—
run