CadEval — leaderboard

CAD and technical-code evaluation tasks for model coding capability tracking.

Metric: Score (self-reported). Source: benchmarklist.com. Status: saturation imminent. 10 models tracked.

Top models

#ModelScore
1O374
2Gemini 2.5 Pro64
3O4 Mini (Medium)62
4O156
5Claude 3.7 Sonnet54
6GPT-4.142
7Gemini 1.5 Flash34
8Claude 3.5 Haiku32
9GPT-4o26
10GPT-4.1 Mini16

Interactive version: theaggregate.ai/benchmark?slug=cadeval · How the rankings work · Data refreshed daily, snapshot 2026-07-22.