{"benchmark_id":"arc-e","benchmark_name":"ARC-E","benchmark_description":"ARC-E (AI2 Reasoning Challenge - Easy Set) is a subset of grade-school level, multiple-choice science questions that requires knowledge and reasoning capabilities. Part of the AI2 Reasoning Challenge dataset containing 5,197 questions that test scientific reasoning and factual knowledge. The Easy Set contains questions that are answerable by retrieval-based and word co-occurrence algorithms, making them more accessible than the Challenge Set.","max_score":1.0,"categories":["reasoning","general"],"modality":"text","total_models":8,"entries":[{"rank":1,"model_id":"gemma-2-27b-it","model_name":"Gemma 2 27B","organization_name":"Google","organization_id":"google","benchmark_score":0.886,"normalized_score":0.886,"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":2,"model_id":"gemma-2-9b-it","model_name":"Gemma 2 9B","organization_name":"Google","organization_id":"google","benchmark_score":0.88,"normalized_score":0.88,"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":3,"model_id":"hermes-3-70b","model_name":"Hermes 3 70B","organization_name":"Nous Research","organization_id":"nous-research","benchmark_score":0.8295,"normalized_score":0.8295,"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":4,"model_id":"gemma-3n-e4b","model_name":"Gemma 3n E4B","organization_name":"Google","organization_id":"google","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":"2025-06-26","announcement_date":"2025-06-26","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":5,"model_id":"gemma-3n-e4b-it-litert-preview","model_name":"Gemma 3n E4B Instructed LiteRT Preview","organization_name":"Google","organization_id":"google","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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":1910000000,"is_new":false},{"rank":6,"model_id":"gemma-3n-e2b","model_name":"Gemma 3n E2B","organization_name":"Google","organization_id":"google","benchmark_score":0.758,"normalized_score":0.758,"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":"2025-06-26","announcement_date":"2025-06-26","multimodal":true,"param_count":8000000000,"is_new":false},{"rank":7,"model_id":"gemma-3n-e2b-it-litert-preview","model_name":"Gemma 3n E2B Instructed LiteRT (Preview)","organization_name":"Google","organization_id":"google","benchmark_score":0.758,"normalized_score":0.758,"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":"2025-05-20","announcement_date":"2025-05-20","multimodal":true,"param_count":1910000000,"is_new":false},{"rank":8,"model_id":"ernie-4.5","model_name":"ERNIE 4.5","organization_name":"Baidu","organization_id":"baidu","benchmark_score":0.607,"normalized_score":0.607,"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}]}