{"benchmark_id":"autologi","name":"AutoLogi","parent_benchmark":null,"categories":["reasoning"],"modality":"text","multilingual":true,"max_score":1.0,"language":"en","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.","paper_link":"https://arxiv.org/abs/2502.16906","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:21.814050+00:00","updated_at":"2026-10-31T18:28:16.405572+00:00","statistics":{"total_models":3,"average_score":0.894,"min_score":0.892,"max_score":0.895,"score_stddev":0.0017320508075688468,"verified_count":0,"self_reported_count":3},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.895,"normalized_score":0.895,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-07-11","param_count":1000000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":1,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.895,"normalized_score":0.895,"verified":false,"self_reported":true,"self_reported_source":"https://moonshotai.github.io/Kimi-K2/","analysis_method":"Accuracy","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-05","param_count":1000000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"qwen3-14b","model_name":"Qwen3 14B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.892,"normalized_score":0.892,"verified":false,"self_reported":true,"self_reported_source":"https://arxiv.org/abs/2505.09388","analysis_method":"Thinking mode; accuracy; temperature 0.6, top-p 0.95, top-k 20","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.12,"output_cost_per_million":0.24,"context_window":40960,"announcement_date":"2025-04-28","param_count":14000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"DeepInfra"}]}