Benchmark RadarAI BENCHMARK PROFILE
SciMIF
Evaluates instruction following of MLLMs across five scientific disciplines with a taxonomy of 10 constraint groups.
- Released
- 2026-08-26
- Readiness
- Runnable
- Primary field
- Science & Research
Why it matters
Fills the gap in multimodal instruction adherence in scientific applications, revealing discipline-specific challenges.
Motivation
Understanding instruction-following capabilities in scientific domains is essential for effectively leveraging Multimodal Large Language Models (MLLMs) to advance the development of scientific fields.
Primary resources
Benchmark Radar records only publicly supported details and links back to primary sources for verification.