Wikibench

Nuscene

reasoning

Multilingual: no

A multimodal benchmark for scene understanding and reasoning over the nuScenes autonomous driving domain.

Methodology

Imported from llm-stats public benchmark metadata. Modality: multimodal. Max score: 1. Categories: multimodal, reasoning, spatial, vision. Language: en. Verified by llm-stats: no.

Leaderboard

Showing 3 of 3 results

  1. Qwen3.5-122B-A10B self-reported llm-stats
    15.4%
  2. Qwen3.5-27B self-reported llm-stats
    15.2%
  3. Qwen3.5-35B-A3B self-reported llm-stats
    14.6%