← mecheval / task / a2-washer-01

Annular washer A · A2 · a2-washer-01

axisymmetric · boolean · washer

Expected

Prompt

Make a flat circular washer. Outer diameter 50mm, inner diameter 25mm, thickness 5mm. Axis along Z, base on the XY plane (z = 0 to z = 5). The bore is a single concentric through-hole. Output a single solid.

Checks

0
valid_solid
{
  "type": "valid_solid"
}
1
bbox
{
  "type": "bbox",
  "min": [
    -25,
    -25,
    0
  ],
  "max": [
    25,
    25,
    5
  ],
  "tolerance_mm": 0.1
}
2
mass_props
{
  "type": "mass_props",
  "volume_mm3": 7363.11,
  "center_of_mass": [
    0,
    0,
    2.5
  ],
  "tolerance_pct": 1
}
3
hole_count
{
  "type": "hole_count",
  "diameter_mm": 25,
  "expected": 1,
  "diameter_tolerance_mm": 0.1
}
4
hole_positions
{
  "type": "hole_positions",
  "diameter_mm": 25,
  "positions": [
    [
      0,
      0,
      0
    ]
  ],
  "tolerance_mm": 0.15
}
5
step_roundtrip
{
  "type": "step_roundtrip",
  "tolerance_pct": 1
}

Anti-cheese

{
  "max_solid_count": 1
}

Limits

{
  "max_tokens": 20000,
  "max_wallclock_sec": 120,
  "max_tool_calls": 20
}

Recent attempts

Runs (35)

modelrun statusscorefirst failtokenswall
claude-mcp-claude-opus-4-7 20260611T180607Z-506c PASS 1.00 181.8k 35.3s
claude-mcp-claude-opus-4-7 20260611T180601Z-77d8 PASS 1.00 181.5k 36.4s
claude-mcp-claude-opus-4-7 20260611T180529Z-ed19 PASS 1.00 267.8k 49.3s
claude-mcp-claude-opus-4-7 20260611T180529Z-18d1 fail 0.83 mass_props · volume off by 166.2% 160.4k 32.2s
claude-mcp-claude-opus-4-7 20260611T180459Z-55fc PASS 1.00 163.9k 30.1s
openai-direct-gpt-5-mini 20260428T213736Z-b325 PASS 1.00 1.1k 7.1s
openai-direct-gpt-5-mini 20260428T213726Z-3c4a PASS 1.00 1.4k 10.3s
openai-direct-gpt-5-mini 20260428T213717Z-ccb0 PASS 1.00 1.3k 8.8s
openai-direct-gpt-5-mini 20260428T213707Z-50c4 PASS 1.00 1.2k 9.7s
openai-direct-gpt-5 20260428T213657Z-d642 PASS 1.00 1.3k 10.5s
openai-direct-gpt-5-mini 20260428T213655Z-fc3d PASS 1.00 1.4k 11.2s
openai-direct-gpt-5 20260428T213646Z-1dc0 PASS 1.00 1.2k 10.8s
openai-direct-gpt-5 20260428T213637Z-77ca PASS 1.00 1.2k 8.4s
openai-direct-gpt-5 20260428T213628Z-6b9f PASS 1.00 1.2k 9.1s
openai-direct-gpt-5 20260428T213607Z-d91a PASS 1.00 1.6k 21.3s
openai-direct-gpt-4o-mini 20260428T212849Z-2c92 PASS 1.00 806 4.0s
openai-direct-gpt-4o-mini 20260428T212846Z-0610 PASS 1.00 796 3.4s
openai-direct-gpt-4o-mini 20260428T212842Z-f603 fail 0.00 valid_solid · solid invalid 816 3.5s
openai-direct-gpt-4o-mini 20260428T212837Z-fa48 fail 0.00 valid_solid · solid invalid 816 4.7s
openai-direct-gpt-4o-mini 20260428T212834Z-fb11 PASS 1.00 804 3.7s
claude-direct-claude-sonnet-4-6 20260428T211652Z-7128 PASS 1.00 850 3.0s
claude-direct-claude-sonnet-4-6 20260428T211649Z-6c49 PASS 1.00 850 2.8s
claude-direct-claude-sonnet-4-6 20260428T211646Z-7a64 PASS 1.00 855 3.0s
claude-direct-claude-sonnet-4-6 20260428T211642Z-5fb9 PASS 1.00 850 3.3s
claude-direct-claude-sonnet-4-6 20260428T211639Z-4b2d PASS 1.00 839 3.1s
claude-direct-claude-haiku-4-5-20251001 20260428T211514Z-b30c fail 0.00 valid_solid · solid invalid 932 2.2s
claude-direct-claude-haiku-4-5-20251001 20260428T211512Z-2e83 PASS 1.00 914 1.9s
claude-direct-claude-haiku-4-5-20251001 20260428T211511Z-beae fail 0.00 valid_solid · solid invalid 876 1.7s
claude-direct-claude-haiku-4-5-20251001 20260428T211509Z-7ed5 PASS 1.00 914 1.7s
claude-direct-claude-opus-4-7 20260428T211508Z-5200 PASS 1.00 1.1k 3.8s
claude-direct-claude-haiku-4-5-20251001 20260428T211507Z-b913 fail 0.00 valid_solid · solid invalid 919 1.8s
claude-direct-claude-opus-4-7 20260428T211504Z-cd98 PASS 1.00 1.1k 3.9s
claude-direct-claude-opus-4-7 20260428T211500Z-9162 PASS 1.00 1.1k 3.6s
claude-direct-claude-opus-4-7 20260428T211456Z-5566 PASS 1.00 1.1k 3.9s
claude-direct-claude-opus-4-7 20260428T211452Z-9ac3 PASS 1.00 1.1k 4.2s

generated 2026-06-17T03:16:07.222Z · static site, regenerate with npm run build -w @mecheval/leaderboard