{"id":247,"count":4,"description":"AI benchmark coverage: what MMLU, GPQA, SWE-bench, Terminal-Bench and ARC-AGI actually measure, who leads each one, and how to read a vendor's claim critically.","link":"https:\/\/convly.ai\/fr\/category\/ai-benchmarks\/","name":"R\u00e9f\u00e9rences d\u2019IA","slug":"ai-benchmarks","taxonomy":"category","parent":0,"meta":[],"_links":{"self":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/categories\/247","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/categories"}],"about":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/taxonomies\/category"}],"wp:post_type":[{"href":"https:\/\/convly.ai\/fr\/wp-json\/wp\/v2\/posts?categories=247"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}