Table of Contents - F.748.44 (03/2025) - Assessment criteria for foundation models – Benchmark

1	Scope
2	References
3	Definitions
	3.1	Terms defined elsewhere
	3.2	Terms defined in this Recommendation
4	Abbreviations and acronyms
5	Conventions
6	Overview of benchmark for foundation models
	6.1	General
	6.2	Testing capabilities
	6.3	Testing datasets
	6.4	Testing method
	6.5	Testing tool
7	Requirements of foundation models
	7.1	Understanding ability
	7.2	Generation ability
	7.3	Reasoning ability
	7.4	Knowledge ability
	7.5	Reliability
	7.6	Robustness
8	Evaluation methods of foundation models
	8.1	Automated evaluation
	8.2	Manual evaluation
Appendix I – Use cases of benchmark testing