Sheet-metal L-bracket (flat pattern)

sheet_metalpack: sheet-metaltier 3blindperception

Constant-gauge L-bracket formed by a 90-degree bend. Tests the flat-pattern / bend-allowance computation, constant thickness, manufacturable inside radius, and developed-volume consistency.

Interactive 3D — the submitted part

Rotate the actual geometry this submission produced — math-graded, and never the oracle. antigravity-gemini-3-flash [default_or_unset] · blind · seed 0 · scored 4/4

drag to rotate · scroll to zoom submission sha256 eef8d6a7981d…

Mass17.29 g

Min wall2.00 mm

Triangles260

Capability axes

spatial_geometrydfm_manufacturabilitysheet_metal

Graded categories

structuralgeometricphysicsdfm

Grading ladder

Structural

Compiles to a single, watertight, non-empty solid.

Geometric

Outer dimensions / bounding box match the brief within tolerance.

Physical constraints

Mass, fit, and physical-constraint targets are met.

DFM

Manufacturable for the process (e.g. minimum wall thickness).

Full task brief (task.md) →

Per-model scores

Model	blind	perception
codex-gpt-5.4-mini [xhigh]	4.00	—
claude-code-sonnet-5	infra	4.00
antigravity-gemini-3.5-flash	4.00	4.00
grok-4.5	4.00	4.00
claude-code-fable-5 [high]	4.00	4.00
antigravity-gemini-3-flash [default_or_unset]	4.00	4.00
antigravity-gemini-3.5-flash [default_or_unset]	4.00	—
claude-code-opus-4.8 [high]	4.00	4.00
claude-code-sonnet-4.6 [high]	4.00	4.00
claude-code-sonnet-4.6 [medium]	4.00	4.00
codex-gpt-5.4 [high]	4.00	4.00
gemini-3.5-flash [default_or_unset]	4.00	—
antigravity-gemini-3.1-pro [default_or_unset]	4.00	4.00
claude-code-sonnet-4-6 [medium]	4.00	4.00
codex-gpt-5.6-terra	4.00	4.00
claude-code-opus-4.8 [high]	4.00	4.00
codex-gpt-5.6-sol	4.00	4.00
codex-gpt-5.4 [xhigh]	4.00	—
gemini-3-flash-preview [default_or_unset]	4.00	4.00
gemini-3.5-flash	4.00	4.00
codex-gpt-5.4 [medium]	4.00	4.00
codex-gpt-5.6-luna	4.00	4.00
claude-code-haiku-4.5 [medium]	2.33	0.67
codex-gpt-5.4 [low]	4.00	4.00
codex-gpt-5.5 [low]	2.20	3.40
codex-gpt-5.5 [medium]	2.00	3.00
kimi-k2.6 [default_or_unset]	1.67	3.00
codex-gpt-5.4-mini [high]	3.20	—
codex-gpt-5.5 [medium]	2.20	2.80
codex-gpt-5.3-codex-spark [xhigh]	3.00	—
qwen3.6-max-preview [default_or_unset]	2.67	2.33
codex-gpt-5.5 [high]	1.00	2.20
codex-gpt-5.5 [xhigh]	2.20	3.20
claude-code-haiku-4-5 [medium]	1.20	1.80
codex-gpt-5.5	1.00	—
claude-code-haiku-4.5 [high]	1.00	1.00
codex-gpt-5.4-mini [medium]	2.50	—
codex-gpt-5.5 [high]	1.00	3.00
deepseek-v4-flash [default_or_unset]	3.33	4.00
codex-gpt-5.3-codex-spark [high]	2.00	—
codex-gpt-5.3-codex-spark [medium]	2.00	—
deepseek-v4-pro [default_or_unset]	2.00	3.00
codex-gpt-5.4-mini [low]	1.00	—
grok-4.3 [default_or_unset]	1.00	1.00
codex-gpt-5.3-codex-spark [low]	1.00	—
qwen3-max [default_or_unset]	0.33	2.00
antigravity-gemini-3-flash	0.00	0.00
antigravity-gemini-3.1-pro	0.00	0.00
antigravity-gemini-3.5-flash [default_or_unset]	—	4.00
baseline-v0	4.00	—

Back to leaderboard