Benchmark RadarAI BENCHMARK PROFILE
PosterBench
PosterBench evaluates academic paper-to-poster generation. It includes a 100-paper Main Track across five disciplines and a 10-paper mini subset, with automated scoring and human evaluation.
- Released
- 2026-08-13
- Readiness
- Runnable
- Primary field
- General AI
Why it matters
It provides a standardized way to compare agentic design systems on long-horizon multimodal generation, enabling measurement of quality and agent efficiency across different models and harnesses.
Motivation
Transforming multimodal sources into condensed and structured media outputs can be fundamentally conceptualized as a long-horizon agentic process centered on a model-harness system.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.