{"benchmark_id":"zclawbench","name":"ZClawBench","parent_benchmark":null,"categories":["agents","coding"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"ZClawBench evaluates Claw-style agent task execution quality, measuring a model's ability to autonomously complete complex multi-step coding tasks in real-world environments.","paper_link":null,"implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:27.045868+00:00","updated_at":"2026-07-05T18:28:06.370819+00:00","statistics":{"total_models":4,"average_score":0.56975,"min_score":0.526,"max_score":0.643,"score_stddev":0.053531143583276194,"verified_count":0,"self_reported_count":4},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.643,"normalized_score":0.643,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.7","analysis_method":"QwenClawBench real-user-distribution Claw agent benchmark","verification_date":null,"provider_id":"novita","input_cost_per_million":1.25,"output_cost_per_million":3.75,"context_window":1000000,"announcement_date":"2026-05-19","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":2,"model_id":"glm-5v-turbo","model_name":"GLM-5V-Turbo","organization_id":"zai-org","organization_name":"Zhipu AI","organization_country":"CN","score":0.576,"normalized_score":0.576,"verified":false,"self_reported":true,"self_reported_source":"https://docs.z.ai/guides/vlm/glm-5v-turbo","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-02","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.534,"normalized_score":0.534,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-27b","analysis_method":"Real-user-distribution Claw agent benchmark, 256K ctx, temp=0.6","verification_date":null,"provider_id":"novita","input_cost_per_million":0.6,"output_cost_per_million":3.6,"context_window":262144,"announcement_date":"2026-04-21","param_count":27781427952,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":4,"model_id":"qwen3.6-35b-a3b","model_name":"Qwen3.6-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.526,"normalized_score":0.526,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-35b-a3b","analysis_method":"Internal real-user-distribution Claw agent benchmark, 256K ctx","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-04-16","param_count":35000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null}]}