{"benchmark_id":"tau3-telecom","benchmark_name":"Tau3 Telecom","benchmark_description":"τ³-Bench telecom domain evaluates agentic models on multi-turn, tool-using customer-support and troubleshooting scenarios in a simulated telecommunications environment.","max_score":1.0,"categories":["reasoning","agents","communication","tool_calling"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"mistral-medium-3-5","model_name":"Mistral Medium 3.5","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.914,"normalized_score":0.914,"verified":false,"self_reported":true,"provider_id":"mistral","input_cost_per_million":1.5,"output_cost_per_million":7.5,"speed_rps":null,"context_window":256000,"release_date":"2026-04-29","announcement_date":"2026-04-29","multimodal":true,"param_count":128000000000,"is_new":false}]}