Assessment criteria for foundation models – Benchmark
Recommendation · Metadata verified · In force
THEME 01 · Foundation Models Evaluation & Assessment
Foundation Models Evaluation & Assessment
Explore how foundation models are tested, compared and assessed, from general capabilities to multimodal tasks.
READING PATH
What does this theme explore?
01
General evaluation & benchmarks
02
Visual, temporal & multimodal evaluation
03
System adaptation & inference performance
Introductions and reading paths are editorial summaries. Consult the originals for the official scope.
01
Browse this themeRelated records
7 catalog recordsRequirements and framework for evaluation of multimodal foundation models
Project records · Metadata verified · Approved on 2026-06-13
Assessment criteria for foundation models – General
Recommendation · Metadata verified · In force
Assessment criteria for foundation models - Vision
Project records · Metadata verified · Approved on 2026-08-29
Evaluation Method for Adaptability of AI Systems to Foundation Models
Project records · Metadata verified · Under study
Performance evaluation methods for large language model inference service
Project records · Metadata verified · Under study
02
Diagrams, animations & videos
Explanatory media to be addedDiagram · media to be added
imageEvaluation & assessment · Concept diagram
Dimensions and workflow of model evaluation
Animation · media to be added
animationEvaluation & assessment · Process animation
How inputs, tasks, metrics and evaluation results connect
Video · media to be added
videoEvaluation & assessment · Introduction & case video
Model evaluation methods and practical testing scenarios
QUESTIONS TO EXPLORE
Questions for further reading
- How can I find Recommendations on foundation model evaluation?
- How does multimodal evaluation differ from general benchmarks?
Knowledge Q&A is being prepared. For now, explore the catalog and original sources.