{"benchmark_id":"swe-atlas-test-writing","benchmark_name":"SWE Atlas - Test Writing","benchmark_description":"SWE Atlas - Test Writing evaluates a model's ability to author meaningful tests for real-world software projects, measuring how well agents can understand code and produce correct, useful test coverage.","max_score":1.0,"categories":["agents","code"],"modality":"text","total_models":1,"entries":[{"rank":1,"model_id":"minimax-m3","model_name":"MiniMax M3","organization_name":"MiniMax","organization_id":"minimax","benchmark_score":0.3083,"normalized_score":0.3083,"verified":false,"self_reported":true,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":1.2,"speed_rps":null,"context_window":1000000,"release_date":"2026-06-01","announcement_date":"2026-06-01","multimodal":true,"param_count":428000000000,"is_new":false}]}