← mecheval / task / a2-flanged-cap-01

Flanged cap with bolt circle A · A2 · a2-flanged-cap-01

flange · bolt-circle · axisymmetric · multi-hole

Expected

Prompt

Make a circular flanged cap. Outer cylinder: outside diameter 60mm, height 8mm, axis along Z, base on the XY plane (z = 0 to z = 8). Concentric central through-hole of diameter 40mm, axis along Z. Six bolt holes of diameter 5mm on a 50mm bolt circle (radius 25mm from the axis), evenly spaced starting at 0 degrees, all parallel to Z and going fully through. Output a single solid.

Checks

0
valid_solid
{
  "type": "valid_solid"
}
1
bbox
{
  "type": "bbox",
  "min": [
    -30,
    -30,
    0
  ],
  "max": [
    30,
    30,
    8
  ],
  "tolerance_mm": 0.1
}
2
mass_props
{
  "type": "mass_props",
  "volume_mm3": 11623.89,
  "center_of_mass": [
    0,
    0,
    4
  ],
  "tolerance_pct": 0.5
}
3
hole_count
{
  "type": "hole_count",
  "diameter_mm": 40,
  "expected": 1,
  "diameter_tolerance_mm": 0.1
}
4
hole_count
{
  "type": "hole_count",
  "diameter_mm": 5,
  "expected": 6,
  "diameter_tolerance_mm": 0.05
}
5
hole_positions
{
  "type": "hole_positions",
  "diameter_mm": 5,
  "positions": [
    [
      25,
      0,
      0
    ],
    [
      12.5,
      21.65,
      0
    ],
    [
      -12.5,
      21.65,
      0
    ],
    [
      -25,
      0,
      0
    ],
    [
      -12.5,
      -21.65,
      0
    ],
    [
      12.5,
      -21.65,
      0
    ]
  ],
  "tolerance_mm": 0.15
}
6
step_roundtrip
{
  "type": "step_roundtrip",
  "tolerance_pct": 1
}

Anti-cheese

{
  "max_solid_count": 1
}

Limits

{
  "max_tokens": 80000,
  "max_wallclock_sec": 360,
  "max_tool_calls": 80
}

Recent attempts

Runs (40)

modelrun statusscorefirst failtokenswall
claude-mcp-claude-opus-4-7 20260611T174139Z-2d08 fail 0.43 bbox · Z off by +2.00mm 630.0k 126.6s
claude-mcp-claude-opus-4-7 20260611T174133Z-2beb fail 0.43 bbox · Z off by +2.00mm 660.3k 131.0s
claude-mcp-claude-opus-4-7 20260611T174123Z-ef20 PASS 1.00 325.0k 68.1s
claude-mcp-claude-opus-4-7 20260611T174002Z-427f PASS 1.00 453.4k 90.8s
claude-mcp-claude-opus-4-7 20260611T173841Z-da87 PASS 1.00 597.0k 177.4s
openai-direct-gpt-5-mini 20260428T213435Z-71b4 fail 0.86 mass_props · volume off by 0.6% 3.3k 33.5s
openai-direct-gpt-5-mini 20260428T213348Z-86aa fail 0.86 mass_props · volume off by 0.6% 3.1k 46.8s
openai-direct-gpt-5-mini 20260428T213317Z-2bd7 PASS 1.00 3.2k 30.3s
openai-direct-gpt-5 20260428T213300Z-9f7d fail 0.86 mass_props · volume off by 0.6% 3.1k 34.3s
openai-direct-gpt-5-mini 20260428T213232Z-abde PASS 1.00 3.0k 43.8s
openai-direct-gpt-5 20260428T213221Z-f46b fail 0.86 mass_props · volume off by 0.6% 3.8k 38.6s
openai-direct-gpt-5-mini 20260428T213147Z-826f PASS 1.00 3.3k 44.1s
openai-direct-gpt-5 20260428T213134Z-83dc fail 0.86 mass_props · volume off by 0.6% 3.8k 46.9s
openai-direct-gpt-5 20260428T213101Z-4f70 fail 0.86 mass_props · volume off by 0.6% 2.9k 32.8s
openai-direct-gpt-5 20260428T213024Z-27e5 fail 0.86 mass_props · volume off by 0.6% 3.0k 36.2s
openai-direct-gpt-4o-mini 20260428T212734Z-4748 fail 0.00 valid_solid · solid invalid 1.3k 12.9s
openai-direct-gpt-4o-mini 20260428T212727Z-1fbd fail 0.00 valid_solid · solid invalid 1.0k 6.7s
openai-direct-gpt-4o-mini 20260428T212654Z-34a8 fail 0.00 valid_solid · solid invalid 1.9k 19.3s
openai-direct-gpt-4o-mini 20260428T212636Z-19f4 fail 0.00 valid_solid · solid invalid 1.6k 18.6s
claude-direct-claude-sonnet-4-6 20260428T211552Z-3159 PASS 1.00 1.9k 12.4s
claude-direct-claude-sonnet-4-6 20260428T211539Z-8234 PASS 1.00 1.9k 12.7s
claude-direct-claude-sonnet-4-6 20260428T211525Z-e541 PASS 1.00 1.9k 12.7s
claude-direct-claude-sonnet-4-6 20260428T211511Z-8102 PASS 1.00 1.9k 12.5s
claude-direct-claude-sonnet-4-6 20260428T211501Z-28a8 PASS 1.00 1.9k 9.9s
claude-direct-claude-haiku-4-5-20251001 20260428T211441Z-1051 fail 0.00 valid_solid · solid invalid 2.2k 6.4s
claude-direct-claude-haiku-4-5-20251001 20260428T211434Z-23f7 fail 0.00 valid_solid · solid invalid 2.2k 6.7s
claude-direct-claude-haiku-4-5-20251001 20260428T211426Z-7999 fail 0.00 valid_solid · solid invalid 2.6k 7.8s
claude-direct-claude-haiku-4-5-20251001 20260428T211419Z-e48d fail 0.00 valid_solid · solid invalid 2.4k 7.2s
claude-direct-claude-haiku-4-5-20251001 20260428T211413Z-217b fail 0.00 valid_solid · solid invalid 2.1k 6.2s
claude-direct-claude-opus-4-7 20260428T205703Z-1893 PASS 1.00 2.3k 10.5s
claude-direct-claude-opus-4-7 20260428T205652Z-d6f3 PASS 1.00 2.0k 9.7s
claude-direct-claude-opus-4-7 20260428T205641Z-8767 PASS 1.00 2.2k 10.4s
claude-direct-claude-opus-4-7 20260428T205630Z-575d PASS 1.00 2.0k 9.8s
claude-direct-claude-opus-4-7 20260428T205618Z-c81e PASS 1.00 2.2k 10.7s
claude-direct-claude-opus-4-7 20260428T153537Z-97a4 PASS 1.00 2.3k 11.5s
claude-direct-claude-opus-4-7 20260428T153525Z-72cb PASS 1.00 2.2k 11.7s
claude-direct-claude-opus-4-7 20260428T153513Z-1961 PASS 1.00 2.3k 11.4s
claude-mcp-claude-opus-4-7 20260428T150052Z-bb98 fail 0.43 mass_props · volume off by 195.4% 610.0k 157.7s
claude-direct-claude-opus-4-7 20260428T142511Z-8f59 PASS 1.00 2.1k 10.4s
claude-direct-claude-opus-4-7 20260428T141650Z-bd80 PASS 1.00 2.0k 15.8s

generated 2026-06-17T03:16:07.210Z · static site, regenerate with npm run build -w @mecheval/leaderboard