{"benchmark_id":"advancedif","benchmark_name":"AdvancedIF","benchmark_description":"AdvancedIF is a rubric-based benchmark measuring complex, multi-turn, and system-prompted instruction following ability, scored with a calibrated LLM judge against per-instruction rubrics.","max_score":1.0,"categories":["reasoning","instruction_following","general"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"mai-thinking-1","model_name":"MAI-Thinking-1","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.85,"normalized_score":0.85,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-06-02","announcement_date":"2026-06-02","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":2,"model_id":"mai-code-1-flash","model_name":"MAI-Code-1-Flash","organization_name":"Microsoft","organization_id":"microsoft","benchmark_score":0.714,"normalized_score":0.714,"verified":false,"self_reported":true,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"speed_rps":null,"context_window":null,"release_date":"2026-06-02","announcement_date":"2026-06-02","multimodal":false,"param_count":null,"is_new":false}]}