Wikibench

ARKitScenes

vision

Multilingual: no

ARKitScenes evaluates 3D scene understanding and spatial reasoning in AR/VR contexts.

Methodology

Imported from llm-stats public benchmark metadata. Modality: multimodal. Max score: 100. Categories: 3d, spatial_reasoning, vision. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 1 of 1 result

  1. Qwen3 VL 235B A22B Thinking self-reported llm-stats
    53.7%