{"benchmark_id":"gsm-8k-(cot)","name":"GSM-8K (CoT)","parent_benchmark":null,"categories":["math","reasoning"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","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.","paper_link":"https://arxiv.org/abs/2110.14168","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:23.673125+00:00","updated_at":"2026-07-05T18:27:49.480806+00:00","statistics":{"total_models":2,"average_score":0.8979999999999999,"min_score":0.845,"max_score":0.951,"score_stddev":0.07495331880577395,"verified_count":0,"self_reported_count":2},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"llama-3.1-70b-instruct","model_name":"Llama 3.1 70B Instruct","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":0.951,"normalized_score":0.951,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct","analysis_method":"8-shot Chain-of-Thought","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-07-23","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},{"rank":2,"model_id":"llama-3.1-8b-instruct","model_name":"Llama 3.1 8B Instruct","organization_id":"meta","organization_name":"Meta","organization_country":"US","score":0.845,"normalized_score":0.845,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct","analysis_method":"8-shot","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2024-07-23","param_count":8000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}