← mecheval / task / a1-cone-01

Truncated cone (frustum) A · A1 · a1-cone-01

primitives · cone · frustum

Expected

Prompt

Make a truncated cone with bottom radius 20mm, top radius 10mm, and height 30mm. Axis along Z, base on the XY plane (z = 0 to z = 30). Output a single solid.

Checks

0
valid_solid
{
  "type": "valid_solid"
}
1
bbox
{
  "type": "bbox",
  "min": [
    -20,
    -20,
    0
  ],
  "max": [
    20,
    20,
    30
  ],
  "tolerance_mm": 0.1
}
2
mass_props
{
  "type": "mass_props",
  "volume_mm3": 21991.15,
  "tolerance_pct": 2
}
3
step_roundtrip
{
  "type": "step_roundtrip",
  "tolerance_pct": 2
}

Anti-cheese

{
  "max_solid_count": 1
}

Limits

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

Recent attempts

Runs (37)

modelrun statusscorefirst failtokenswall
claude-mcp-claude-opus-4-7 20260611T171120Z-4100 PASS 1.00 45.6k 11.3s
claude-mcp-claude-opus-4-7 20260611T171110Z-f3df PASS 1.00 45.6k 10.1s
claude-mcp-claude-opus-4-7 20260611T171103Z-ec6b PASS 1.00 45.6k 40.6s
claude-mcp-claude-opus-4-7 20260611T171053Z-75d7 PASS 1.00 45.6k 10.1s
claude-mcp-claude-opus-4-7 20260611T171044Z-fa2f PASS 1.00 45.6k 9.1s
openai-direct-gpt-5-mini 20260428T212945Z-893c PASS 1.00 960 6.7s
openai-direct-gpt-5-mini 20260428T212939Z-d8f2 PASS 1.00 1.0k 6.6s
openai-direct-gpt-5-mini 20260428T212930Z-b46c PASS 1.00 1.0k 8.9s
openai-direct-gpt-5-mini 20260428T212920Z-0a8f PASS 1.00 1.1k 9.5s
openai-direct-gpt-5-mini 20260428T212914Z-d7cd PASS 1.00 960 5.8s
openai-direct-gpt-5 20260428T212816Z-31d2 PASS 1.00 1.3k 11.0s
openai-direct-gpt-5 20260428T212810Z-2cca PASS 1.00 1.0k 6.0s
openai-direct-gpt-5 20260428T212758Z-ea4e PASS 1.00 1.2k 12.2s
openai-direct-gpt-5 20260428T212751Z-62c4 PASS 1.00 1.0k 7.2s
openai-direct-gpt-5 20260428T212746Z-027a PASS 1.00 895 4.9s
openai-direct-gpt-4o-mini 20260428T212600Z-41a8 fail 0.00 valid_solid · solid invalid 695 2.7s
openai-direct-gpt-4o-mini 20260428T212558Z-e36f PASS 1.00 696 2.2s
openai-direct-gpt-4o-mini 20260428T212555Z-4fd3 fail 0.00 valid_solid · solid invalid 696 2.5s
openai-direct-gpt-4o-mini 20260428T212553Z-8c37 fail 0.00 valid_solid · solid invalid 696 2.2s
openai-direct-gpt-4o-mini 20260428T212550Z-977b PASS 1.00 695 2.6s
claude-direct-claude-sonnet-4-6 20260428T211425Z-e812 PASS 1.00 778 3.1s
claude-direct-claude-sonnet-4-6 20260428T211422Z-f63c PASS 1.00 778 2.8s
claude-direct-claude-sonnet-4-6 20260428T211419Z-cd42 PASS 1.00 778 2.8s
claude-direct-claude-sonnet-4-6 20260428T211417Z-b852 PASS 1.00 778 2.5s
claude-direct-claude-opus-4-7 20260428T211416Z-7451 PASS 1.00 957 3.0s
claude-direct-claude-sonnet-4-6 20260428T211414Z-b076 PASS 1.00 778 2.7s
claude-direct-claude-opus-4-7 20260428T211414Z-4720 PASS 1.00 957 2.3s
claude-direct-claude-opus-4-7 20260428T211412Z-d178 PASS 1.00 957 2.2s
claude-direct-claude-opus-4-7 20260428T211406Z-48f2 PASS 1.00 957 6.1s
claude-direct-claude-opus-4-7 20260428T211403Z-1030 PASS 1.00 957 2.5s
claude-direct-claude-haiku-4-5-20251001 20260428T211354Z-e94b fail 0.00 valid_solid · solid invalid 788 1.1s
claude-direct-claude-haiku-4-5-20251001 20260428T211353Z-2dba fail 0.00 valid_solid · solid invalid 786 1.1s
claude-direct-claude-haiku-4-5-20251001 20260428T211351Z-d584 fail 0.00 valid_solid · solid invalid 785 1.1s
claude-direct-claude-haiku-4-5-20251001 20260428T211350Z-6a6d fail 0.00 valid_solid · solid invalid 788 1.4s
claude-direct-claude-haiku-4-5-20251001 20260428T211349Z-cca9 fail 0.00 valid_solid · solid invalid 789 1.2s
claude-direct-claude-sonnet-4-6 20260428T211226Z-c5a9 PASS 1.00 778 2.3s
claude-direct-claude-sonnet-4-6 20260428T211224Z-f777 PASS 1.00 778 2.5s

generated 2026-06-17T03:16:07.192Z · static site, regenerate with npm run build -w @mecheval/leaderboard