{"benchmark_id":"openbookqa","name":"OpenBookQA","parent_benchmark":null,"categories":["reasoning","general"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"OpenBookQA is a question-answering dataset modeled after open book exams for assessing human understanding. It contains 5,957 multiple-choice elementary-level science questions that probe understanding of 1,326 core science facts and their application to novel situations, requiring combination of open book facts with broad common knowledge through multi-hop reasoning.","paper_link":"https://arxiv.org/abs/1809.02789","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:25.633943+00:00","updated_at":"2026-07-05T18:27:58.079361+00:00","statistics":{"total_models":5,"average_score":0.716,"min_score":0.494,"max_score":0.896,"score_stddev":0.16227754003558223,"verified_count":0,"self_reported_count":5},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"phi-3.5-moe-instruct","model_name":"Phi-3.5-MoE-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.896,"normalized_score":0.896,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-MoE-instruct","analysis_method":"10-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-23","param_count":60000000000,"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":"phi-3.5-mini-instruct","model_name":"Phi-3.5-mini-instruct","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.792,"normalized_score":0.792,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-3.5-mini-instruct","analysis_method":"10-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-23","param_count":3800000000,"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":"phi-4-mini","model_name":"Phi 4 Mini","organization_id":"microsoft","organization_name":"Microsoft","organization_country":"US","score":0.792,"normalized_score":0.792,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/microsoft/Phi-4-mini-instruct","analysis_method":"10-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-02-01","param_count":3840000000,"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":"mistral-nemo-instruct-2407","model_name":"Mistral NeMo Instruct","organization_id":"mistral","organization_name":"Mistral AI","organization_country":"FR","score":0.606,"normalized_score":0.606,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407","analysis_method":"0-shot evaluation","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-07-18","param_count":12000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"hermes-3-70b","model_name":"Hermes 3 70B","organization_id":"nous-research","organization_name":"Nous Research","organization_country":"US","score":0.494,"normalized_score":0.494,"verified":false,"self_reported":true,"self_reported_source":"https://nousresearch.com/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-08-15","param_count":70000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}