{"benchmark_id":"alignbench","benchmark_name":"AlignBench","benchmark_description":"AlignBench is a comprehensive multi-dimensional benchmark for evaluating Chinese alignment of Large Language Models. It contains 8 main categories: Fundamental Language Ability, Advanced Chinese Understanding, Open-ended Questions, Writing Ability, Logical Reasoning, Mathematics, Task-oriented Role Play, and Professional Knowledge. The benchmark includes 683 real-scenario rooted queries with human-verified references and uses a rule-calibrated multi-dimensional LLM-as-Judge approach with Chain-of-Thought for evaluation.","max_score":1.0,"categories":["language","math","reasoning","roleplay","general","creativity","writing"],"modality":"text","total_models":4,"entries":[{"rank":1,"model_id":"qwen-2.5-72b-instruct","model_name":"Qwen2.5 72B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.816,"normalized_score":0.816,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":72700000000,"is_new":false},{"rank":2,"model_id":"deepseek-v2.5","model_name":"DeepSeek-V2.5","organization_name":"DeepSeek","organization_id":"deepseek","benchmark_score":0.804,"normalized_score":0.804,"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":"2024-05-08","announcement_date":"2024-05-08","multimodal":false,"param_count":236000000000,"is_new":false},{"rank":3,"model_id":"qwen-2.5-7b-instruct","model_name":"Qwen2.5 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.733,"normalized_score":0.733,"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":"2024-09-19","announcement_date":"2024-09-19","multimodal":false,"param_count":7610000000,"is_new":false},{"rank":4,"model_id":"qwen2-7b-instruct","model_name":"Qwen2 7B Instruct","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.721,"normalized_score":0.721,"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":"2024-07-23","announcement_date":"2024-07-23","multimodal":false,"param_count":7620000000,"is_new":false}]}