Benchmark RadarAI BENCHMARK PROFILE
MultivationBench
Evaluates multimodal motivation reasoning in story-driven visual narratives, using 1,000 narratives with 16,092 multi-label questions grounded in Maslow and Reiss frameworks across definition and practical reasoning tasks.
- Released
- 2026-07-29
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
Assesses whether models can reason about evolving character motivations across sequential context, an underexplored capability for social intelligence.
Motivation
Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential motivation reasoning remains insufficiently studied.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.