{"benchmark_id":"gsm-8k-(cot)","benchmark_name":"GSM-8K (CoT)","benchmark_description":"Grade School Math 8K with Chain-of-Thought prompting, featuring 8.5K high-quality linguistically diverse grade school math word problems requiring multi-step reasoning and elementary arithmetic operations.","max_score":1.0,"categories":["math","reasoning"],"modality":"text","total_models":2,"entries":[{"rank":1,"model_id":"llama-3.1-70b-instruct","model_name":"Llama 3.1 70B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.951,"normalized_score":0.951,"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":70000000000,"is_new":false},{"rank":2,"model_id":"llama-3.1-8b-instruct","model_name":"Llama 3.1 8B Instruct","organization_name":"Meta","organization_id":"meta","benchmark_score":0.845,"normalized_score":0.845,"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":8000000000,"is_new":false}]}