{"benchmark_id":"agieval","benchmark_name":"AGIEval","benchmark_description":"A human-centric benchmark for evaluating foundation models on standardized exams including college entrance exams (Gaokao, SAT), law school admission tests (LSAT), math competitions, lawyer qualification tests, and civil service exams. Contains 20 tasks (18 multiple-choice, 2 cloze) designed to assess understanding, knowledge, reasoning, and calculation abilities in real-world academic and professional contexts.","max_score":1.0,"categories":["legal","math","reasoning","general"],"modality":"text","total_models":10,"entries":[{"rank":1,"model_id":"mistral-small-24b-base-2501","model_name":"Mistral Small 3 24B Base","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.658,"normalized_score":0.658,"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":"2025-01-30","announcement_date":"2025-01-30","multimodal":true,"param_count":23600000000,"is_new":false},{"rank":2,"model_id":"ministral-3-14b-base-2512","model_name":"Ministral 3 (14B Base 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.648,"normalized_score":0.648,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":14000000000,"is_new":false},{"rank":3,"model_id":"ministral-3-8b-base-2512","model_name":"Ministral 3 (8B Base 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.591,"normalized_score":0.591,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":4,"model_id":"hermes-3-70b","model_name":"Hermes 3 70B","organization_name":"Nous Research","organization_id":"nous-research","benchmark_score":0.5618,"normalized_score":0.5618,"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":"2024-08-15","announcement_date":"2024-08-15","multimodal":false,"param_count":70000000000,"is_new":false},{"rank":5,"model_id":"gemma-2-27b-it","model_name":"Gemma 2 27B","organization_name":"Google","organization_id":"google","benchmark_score":0.551,"normalized_score":0.551,"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":"2024-06-27","announcement_date":"2024-06-27","multimodal":false,"param_count":27200000000,"is_new":false},{"rank":6,"model_id":"gemma-2-9b-it","model_name":"Gemma 2 9B","organization_name":"Google","organization_id":"google","benchmark_score":0.528,"normalized_score":0.528,"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":"2024-06-27","announcement_date":"2024-06-27","multimodal":false,"param_count":9240000000,"is_new":false},{"rank":7,"model_id":"ministral-3-3b-base-2512","model_name":"Ministral 3 (3B Base 2512)","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.511,"normalized_score":0.511,"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":"2025-12-04","announcement_date":"2025-12-04","multimodal":true,"param_count":3000000000,"is_new":false},{"rank":8,"model_id":"granite-3.3-8b-base","model_name":"Granite 3.3 8B Base","organization_name":"IBM","organization_id":"ibm","benchmark_score":0.493,"normalized_score":0.493,"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":"2025-04-16","announcement_date":"2025-04-16","multimodal":true,"param_count":8170000000,"is_new":false},{"rank":9,"model_id":"ministral-8b-instruct-2410","model_name":"Ministral 8B Instruct","organization_name":"Mistral AI","organization_id":"mistral","benchmark_score":0.483,"normalized_score":0.483,"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":"2024-10-16","announcement_date":"2024-10-16","multimodal":false,"param_count":8019808256,"is_new":false},{"rank":10,"model_id":"ernie-4.5","model_name":"ERNIE 4.5","organization_name":"Baidu","organization_id":"baidu","benchmark_score":0.285,"normalized_score":0.285,"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":"2025-06-25","announcement_date":"2025-06-25","multimodal":false,"param_count":21000000000,"is_new":false}]}