TAR-Bench

What is TAR-Bench?

Evaluates video-language models on ten traffic anomaly reasoning tasks using 960 human-curated test annotations over 80 held-out clips.

Released

2026-08-10

Evaluates

General AI, Multimodal, Reasoning

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.10317

TAR-Bench paper and dataset

• Paper https://arxiv.org/abs/2608.10317
• Dataset https://huggingface.co/datasets/nvidia/PhysicalAI-Traffic-Anomaly-Reasoning

Which sources cite TAR-Bench?

• TAR-Bench

Related General AI, Multimodal, Reasoning benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A-Bench
• A-OKVQA
• A3S-Bench
• AARRI-Bench
• ActBench