{"benchmark_id":"alignbench","name":"AlignBench","parent_benchmark":null,"categories":["math","reasoning","roleplay","language","general","creativity","writing"],"modality":"text","multilingual":true,"max_score":1.0,"language":"en","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.","paper_link":"https://arxiv.org/abs/2311.18743","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:21.540729+00:00","updated_at":"2026-07-05T18:27:42.627999+00:00","statistics":{"total_models":4,"average_score":0.7685000000000001,"min_score":0.721,"max_score":0.816,"score_stddev":0.04841831609353366,"verified_count":0,"self_reported_count":4},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen-2.5-72b-instruct","model_name":"Qwen2.5 72B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.816,"normalized_score":0.816,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5/","analysis_method":"AlignBench v1.1 benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":72700000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"deepseek-v2.5","model_name":"DeepSeek-V2.5","organization_id":"deepseek","organization_name":"DeepSeek","organization_country":"CN","score":0.804,"normalized_score":0.804,"verified":false,"self_reported":true,"self_reported_source":"https://www.deepseek.com/","analysis_method":"Score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-05-08","param_count":236000000000,"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":"qwen-2.5-7b-instruct","model_name":"Qwen2.5 7B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.733,"normalized_score":0.733,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen2.5-llm/","analysis_method":"AlignBench v1.1 benchmark evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-09-19","param_count":7610000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":4,"model_id":"qwen2-7b-instruct","model_name":"Qwen2 7B Instruct","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.721,"normalized_score":0.721,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/Qwen/Qwen2-7B-Instruct","analysis_method":"Score","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-07-23","param_count":7620000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}