{"benchmark_id":"humanity's-last-exam-(with-tools,-text-only)","benchmark_name":"Humanity's Last Exam (with tools, text-only)","benchmark_description":"Text-only Humanity's Last Exam variant evaluated with tool use enabled.","max_score":1.0,"categories":["math","reasoning"],"modality":"text","total_models":3,"entries":[{"rank":1,"model_id":"deepseek-v4-pro-0813","model_name":"DeepSeek-V4-Pro-0813","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.6,"normalized_score":0.6,"verified":false,"self_reported":true,"provider_id":"deepseek","input_cost_per_million":0.435,"output_cost_per_million":0.87,"speed_rps":null,"context_window":1048576,"release_date":"2026-08-13","announcement_date":"2026-08-13","multimodal":false,"param_count":1600000000000,"is_new":false},{"rank":2,"model_id":"qwen3.8-max","model_name":"Qwen3.8 Max","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.562,"normalized_score":0.562,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":1.65,"output_cost_per_million":4.951,"speed_rps":null,"context_window":256000,"release_date":"2026-08-02","announcement_date":"2026-08-02","multimodal":true,"param_count":2400000000000,"is_new":false},{"rank":3,"model_id":"hy3","model_name":"Hy3","organization_name":"Tencent","organization_id":"tencent","benchmark_score":0.532,"normalized_score":0.532,"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":"2026-07-06","announcement_date":"2026-07-06","multimodal":false,"param_count":295000000000,"is_new":false}]}