← mecheval / task / a1-block-01

Rectangular block A · A1 · a1-block-01

primitives · block

Expected

Prompt

Make a rectangular block 60mm long (X) × 40mm wide (Y) × 20mm tall (Z). Center it in X and Y, with the bottom face on the XY plane (z = 0 to z = 20). Output a single solid.

Checks

0
valid_solid
{
  "type": "valid_solid"
}
1
bbox
{
  "type": "bbox",
  "min": [
    -30,
    -20,
    0
  ],
  "max": [
    30,
    20,
    20
  ],
  "tolerance_mm": 0.05
}
2
mass_props
{
  "type": "mass_props",
  "volume_mm3": 48000,
  "center_of_mass": [
    0,
    0,
    10
  ],
  "tolerance_pct": 0.1
}
3
step_roundtrip
{
  "type": "step_roundtrip",
  "tolerance_pct": 0.1
}

Anti-cheese

{
  "max_solid_count": 1
}

Limits

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

Recent attempts

Runs (36)

modelrun statusscorefirst failtokenswall
claude-mcp-claude-opus-4-7 20260612T003038Z-27ed PASS 1.00 175.2k 38.5s
claude-mcp-claude-opus-4-7 20260611T171002Z-ff37 PASS 1.00 229.4k 144.1s
claude-mcp-claude-opus-4-7 20260611T170952Z-bc96 PASS 1.00 248.6k 51.1s
claude-mcp-claude-opus-4-7 20260611T170952Z-ad86 fail 0.50 bbox · X off by +30.00mm 45.6k 9.8s
claude-mcp-claude-opus-4-7 20260611T170952Z-79c6 PASS 1.00 249.0k 77.7s
claude-mcp-claude-opus-4-7 20260611T170952Z-0318 PASS 1.00 248.4k 113.6s
claude-mcp-claude-opus-4-7 20260611T170748Z-92ab PASS 1.00 179.3k 39.3s
openai-direct-gpt-5-mini 20260428T213036Z-2f19 PASS 1.00 1.2k 16.8s
openai-direct-gpt-5-mini 20260428T213024Z-f42d PASS 1.00 1.3k 12.2s
openai-direct-gpt-5-mini 20260428T213013Z-8f6f PASS 1.00 1.2k 11.0s
openai-direct-gpt-5-mini 20260428T213004Z-99ac PASS 1.00 1.1k 9.0s
openai-direct-gpt-5-mini 20260428T212952Z-5fa5 PASS 1.00 1.3k 12.2s
openai-direct-gpt-5 20260428T212905Z-533a PASS 1.00 1.1k 8.1s
openai-direct-gpt-5 20260428T212859Z-ca68 PASS 1.00 1.0k 5.9s
openai-direct-gpt-5 20260428T212851Z-a6e5 PASS 1.00 1.1k 7.8s
openai-direct-gpt-5 20260428T212835Z-e20b PASS 1.00 1.6k 15.6s
openai-direct-gpt-4o-mini 20260428T212616Z-065e fail 0.00 valid_solid · solid invalid 738 2.5s
openai-direct-gpt-4o-mini 20260428T212613Z-2ad3 fail 0.00 valid_solid · solid invalid 740 2.7s
openai-direct-gpt-4o-mini 20260428T212610Z-a8d5 PASS 1.00 772 3.1s
openai-direct-gpt-4o-mini 20260428T212606Z-d541 fail 0.00 valid_solid · solid invalid 742 3.4s
openai-direct-gpt-4o-mini 20260428T212603Z-3c4d fail 0.00 valid_solid · solid invalid 738 3.3s
claude-direct-claude-sonnet-4-6 20260428T211441Z-96ed PASS 1.00 843 3.3s
claude-direct-claude-sonnet-4-6 20260428T211438Z-1c23 PASS 1.00 825 3.2s
claude-direct-claude-sonnet-4-6 20260428T211435Z-ec47 PASS 1.00 825 3.0s
claude-direct-claude-sonnet-4-6 20260428T211432Z-ec8a PASS 1.00 825 3.1s
claude-direct-claude-opus-4-7 20260428T211431Z-2327 PASS 1.00 1.0k 2.6s
claude-direct-claude-sonnet-4-6 20260428T211428Z-e0a2 PASS 1.00 825 3.4s
claude-direct-claude-opus-4-7 20260428T211428Z-d17f PASS 1.00 1.0k 2.9s
claude-direct-claude-opus-4-7 20260428T211425Z-aab8 PASS 1.00 1.0k 2.7s
claude-direct-claude-opus-4-7 20260428T211422Z-bce9 PASS 1.00 1.0k 2.7s
claude-direct-claude-opus-4-7 20260428T211419Z-a9c4 PASS 1.00 1.0k 2.8s
claude-direct-claude-haiku-4-5-20251001 20260428T211401Z-92c7 fail 0.00 valid_solid · solid invalid 883 1.9s
claude-direct-claude-haiku-4-5-20251001 20260428T211400Z-e330 fail 0.00 valid_solid · solid invalid 842 1.5s
claude-direct-claude-haiku-4-5-20251001 20260428T211358Z-a58a fail 0.00 valid_solid · solid invalid 882 1.7s
claude-direct-claude-haiku-4-5-20251001 20260428T211357Z-5bfe PASS 1.00 874 1.4s
claude-direct-claude-haiku-4-5-20251001 20260428T211355Z-14b8 PASS 1.00 846 1.7s

generated 2026-06-17T03:16:07.191Z · static site, regenerate with npm run build -w @mecheval/leaderboard