partforge

Which models can actually do CAD?

14 models, 3 tasks, 84 attempts. Each attempt is graded on whether it built, on measured geometry, and on a checklist an AI judge answers from the renders. Click any number to open the attempt behind it.

All models

Rank by
#ModelCost and timeOverallStrictGate pass
1GPT-5.6 LunaOpenAI
100100%
2Gemini 3.8 FlashGoogle
100100%
3GPT-5.6 TerraOpenAI
100100%
4GPT-5.6 SolOpenAI
100100%
5Sonnet 5Anthropic
100100%
6Grok 4.6xAI
100100%
7Opus 5Anthropic
100100%
8Qwen 3.8 MaxAlibaba
100100%
9Fable 5.1Anthropic
100100%
10Opus 4.8Anthropic
100100%
11Gemini 3.1 ProGoogle
99100%
12Fable 5Anthropic
99100%
13GLM 5.3 Flash (Z.ai)
95100%
14Kimi K3 (Moonshot)
00%

Overall gives partial credit at every layer, so the top of the board bunches. Strict counts only the attempts that got everything right. Gate pass is the share whose part was watertight, hole-correct and overlap-free. Hover any bar for its number. Ties break by cost, then time.

Browse the tasks

How the score is made

Built 30%, measured geometry 50%, AI judge 20%. A failed gate zeroes geometry for that attempt. The AI judges are Opus 4.8. Read the methodology.

This is an older run. See the current results.

Run screen-14-fixed2026-09-04spend $24.32, 3 unpricedOther runs: 2026-09-10T19-44-23-baseline-2026-09, 2026-09-04T20-02-10-stage2-hard-cases