{"benchmark_id":"mm-if-eval","benchmark_name":"MM IF-Eval","benchmark_description":"A challenging multimodal instruction-following benchmark that includes both compose-level constraints for output responses and perception-level constraints tied to input images, with comprehensive evaluation pipeline.","max_score":1.0,"categories":["multimodal","reasoning","structured_output"],"modality":"multimodal","total_models":2,"entries":[{"rank":1,"model_id":"lfm-2.5-vl-3b","model_name":"LFM2.5-VL-3B","organization_name":"Liquid AI","organization_id":"liquid","benchmark_score":0.606,"normalized_score":0.606,"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":"2026-08-12","announcement_date":"2026-08-12","multimodal":true,"param_count":3123483888,"is_new":false},{"rank":2,"model_id":"pixtral-12b-2409","model_name":"Pixtral-12B","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.527,"normalized_score":0.527,"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":"2024-09-17","announcement_date":"2024-09-17","multimodal":true,"param_count":12400000000,"is_new":false}]}