Specialized Benchmarks

Benchmarks dedicated to particular domains: medicine, law, finance, programming, science, Arabic and other languages, built with the participation of domain experts. Excludes general benchmarks, which belong to 9.2, cultural representation and low-resource languages as a field, which belong to 4.11, and actual sector use, which belongs to 10.14.

• 4.11 Localization, Low-Resource Languages and Cultural Representation
• 9.2 General-Task Benchmarks
• 10.14 Sector Case Studies and Integrated Use Cases

• 9.1 Measurement Frameworks and Reference Metrics
• 9.2 General-Task Benchmarks
• 9.4 Evaluating Agentic Systems
• 9.5 Stress and Robustness Testing
• 9.6 Red Teaming and Security Bounties
• 9.7 TEVV, External Audit and Conformity Assessment
• 9.8 Impact Assessment
• 9.9 Reproducibility, Open Science and Benchmark Snapshots