CADEngBench - Assembly End-to-End (A2): leaderboard

Metric: End-to-end pass rate (%; share of 120 assembly relation tasks between two source B-Rep bodies; one response per task whose rank-1 joint is correct and whose predicted joint frame, placement and allowed and blocked motions pass the scripted kinematic tests). Source: arxiv.org. Saturation forecast: Around 2030. 8 models tracked.

Top models

#ModelScore
1Gemini 3 Flash (Preview) (Minimal)15.8
2Claude Sonnet 4.512.5
3GPT-5.2 (Non-reasoning)11.7
4Llama 4 Maverick10.8
5Qwen 3.5 35B A3B (Non-reasoning)10.8
6GLM-4.6V (Non-reasoning)8.3
7Kimi K2.5 (Non-reasoning)7.5

Interactive version: theaggregate.ai/benchmark?slug=cadengbench-assembly-end-to-end-a2 · How It Works · Data refreshed daily, snapshot 2026-09-29.