{"benchmark_id":"autologi","benchmark_name":"AutoLogi","benchmark_description":"AutoLogi is an automated method for synthesizing open-ended logic puzzles to evaluate reasoning abilities of Large Language Models. The benchmark addresses limitations of existing multiple-choice reasoning evaluations by featuring program-based verification and controllable difficulty levels. It includes 1,575 English and 883 Chinese puzzles, enabling more reliable evaluation that better distinguishes models' reasoning capabilities across languages.","max_score":1.0,"categories":["reasoning"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.895,"normalized_score":0.895,"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":"2025-09-05","announcement_date":"2025-09-05","multimodal":false,"param_count":1000000000000,"is_new":false},{"rank":2,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.895,"normalized_score":0.895,"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":"2025-07-11","announcement_date":"2025-07-11","multimodal":false,"param_count":1000000000000,"is_new":false}]}