AgentVidBench

What is AgentVidBench?

Evaluates MLLM agents on 100 multi-hop video question answering tasks with 26 answer choices per question, requiring spatial, temporal, and causal reasoning…

Released

2026-09-18

Evaluates

General AI, Reasoning, Vision & 3D

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2609.21386

AgentVidBench paper, code and dataset

• Paper https://arxiv.org/abs/2609.21386
• Code https://github.com/krafton-ai/agentvidbench
• Dataset https://huggingface.co/datasets/agentvidbench/agentvidbench

Which sources cite AgentVidBench?

• AgentVidBench

Related General AI, Reasoning, Vision & 3D benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 2d-fet-bench
• 3DCodeBench
• 5-Dialects-BN
• A Real-World CAD Segmentation Benchmark
• A-OKVQA
• A3S-Bench
• AARRI-Bench