MechVQA - Assembly Relationship: leaderboard

MechVQA (2026) tests multimodal LLMs on understanding mechanical engineering drawings, with 20,778 questions on 3,281 drawings scored as accuracy by three LLM judges against reference answers. This board covers the Assembly Relationship subtask of the reasoning capability, as accuracy in percent on the test split; higher is better.

Metric: Accuracy (%) on the Assembly Relationship subtask (Reasoning capability), MechVQA test split (drawing-level 8:1:1 split of 20,778 questions on 3,281 mechanical drawings), answers judged against the reference by three LLM judges (GPT-OSS-120B, DeepSeek-V3.2, Kimi-k2); higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 15 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Qwen 3 VL Plus74#512
2Claude Sonnet 4.562#261
3Qwen 3 VL 32B Instruct62#606
4GPT-560#178
5GLM-4.6V60#710
6GPT-4o48#751
7Gemini 3 Pro (Preview)46#119
8Qwen 3 VL 30B A3B Instruct38#895
9InternVL3.5-8B28#1604
10MiMo-VL-7B-SFT26#1089
11Gemma 3 27B (IT)24#1324
12GPT-4o Mini24#1667
13MiniCPM-V-4.524#1441
14Qwen 3 VL 4B Instruct22#1332
15Llama 3.2 11B Instruct0#5174

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=mechvqa-assembly-relationship · How It Works · Data refreshed daily, snapshot 2026-11-21.