{"benchmark_id":"gsm8k-chat","benchmark_name":"GSM8K Chat","benchmark_description":"Grade School Math 8K adapted for chat format evaluation, 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":1,"entries":[{"rank":1,"model_id":"llama-3.1-nemotron-70b-instruct","model_name":"Llama 3.1 Nemotron 70B Instruct","organization_name":"NVIDIA","organization_id":"nvidia","benchmark_score":0.8188,"normalized_score":0.8188,"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":"2024-10-01","announcement_date":"2024-10-01","multimodal":false,"param_count":70000000000,"is_new":false}]}