{"benchmark_id":"zebralogic","benchmark_name":"ZebraLogic","benchmark_description":"ZebraLogic is an evaluation framework for assessing large language models' logical reasoning capabilities through logic grid puzzles derived from constraint satisfaction problems (CSPs). The benchmark consists of 1,000 programmatically generated puzzles with controllable and quantifiable complexity, revealing a 'curse of complexity' where model accuracy declines significantly as problem complexity grows.","max_score":1.0,"categories":["reasoning"],"modality":"text","total_models":8,"entries":[{"rank":1,"model_id":"qwen3-vl-235b-a22b-thinking","model_name":"Qwen3 VL 235B A22B Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.973,"normalized_score":0.973,"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":"2025-09-22","announcement_date":"2025-09-22","multimodal":true,"param_count":236000000000,"is_new":false},{"rank":2,"model_id":"longcat-flash-thinking","model_name":"LongCat-Flash-Thinking","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.955,"normalized_score":0.955,"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":"2025-09-22","announcement_date":"2025-09-22","multimodal":false,"param_count":560000000000,"is_new":false},{"rank":3,"model_id":"qwen3-235b-a22b-instruct-2507","model_name":"Qwen3-235B-A22B-Instruct-2507","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.95,"normalized_score":0.95,"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":"2025-07-22","announcement_date":"2025-07-22","multimodal":false,"param_count":235000000000,"is_new":false},{"rank":4,"model_id":"longcat-flash-chat","model_name":"LongCat-Flash-Chat","organization_name":"Meituan","organization_id":"meituan","benchmark_score":0.893,"normalized_score":0.893,"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":"2025-08-29","announcement_date":"2025-08-29","multimodal":false,"param_count":560000000000,"is_new":false},{"rank":5,"model_id":"kimi-k2-instruct-0905","model_name":"Kimi K2-Instruct-0905","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.89,"normalized_score":0.89,"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":6,"model_id":"kimi-k2-instruct","model_name":"Kimi K2 Instruct","organization_name":"Moonshot AI","organization_id":"moonshotai","benchmark_score":0.89,"normalized_score":0.89,"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},{"rank":7,"model_id":"minimax-m1-80k","model_name":"MiniMax M1 80K","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.868,"normalized_score":0.868,"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":"2025-06-16","announcement_date":"2025-06-16","multimodal":false,"param_count":456000000000,"is_new":false},{"rank":8,"model_id":"minimax-m1-40k","model_name":"MiniMax M1 40K","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.801,"normalized_score":0.801,"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":"2025-06-16","announcement_date":"2025-06-16","multimodal":false,"param_count":456000000000,"is_new":false}]}