{"benchmark_id":"sifo-multiturn","benchmark_name":"SIFO-Multiturn","benchmark_description":"SIFO-Multiturn evaluates instruction following capabilities in multi-turn conversational settings, testing how well models maintain context and follow instructions across multiple exchanges.","max_score":100.0,"categories":["structured_output","general","agents"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22B Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.711,"normalized_score":0.711,"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":"2025-09-22","announcement_date":"2025-09-22","multimodal":true,"param_count":236000000000,"is_new":false}]}