{"benchmark_id":"claw-eval","name":"Claw-Eval","parent_benchmark":null,"categories":["agents","coding"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"Claw-Eval tests real-world agentic task completion across complex multi-step scenarios, evaluating a model's ability to use tools, navigate environments, and complete end-to-end tasks autonomously.","paper_link":null,"implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:22.368839+00:00","updated_at":"2026-07-17T06:42:46.154713+00:00","statistics":{"total_models":13,"average_score":0.645846153846154,"min_score":0.5,"max_score":0.809,"score_stddev":0.08480256104018534,"verified_count":0,"self_reported_count":13},"child_benchmarks":[{"benchmark_id":"kimi-claw-24-7-bench","name":"Kimi Claw 24/7 Bench","categories":["agents","coding"],"modality":"text","max_score":1.0,"description":"Kimi Claw 24/7 Bench is Moonshot AI's in-house benchmark for evaluating long-horizon agentic performance in persistent, multi-day coworking tasks. It spans 17 professional scenarios across 610 evaluation points, covering software engineering, ML research, recruiting, trading, and marketing tasks executed through the OpenClaw harness."}],"linked_dataset":null,"models":[{"rank":1,"model_id":"kimi-k2.6","model_name":"Kimi K2.6","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.809,"normalized_score":0.809,"verified":false,"self_reported":true,"self_reported_source":"https://www.kimi.com/blog/kimi-k2-6","analysis_method":"pass@3","verification_date":null,"provider_id":"deepinfra","input_cost_per_million":0.75,"output_cost_per_million":3.5,"context_window":262144,"announcement_date":"2026-04-20","param_count":1000000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"DeepInfra","best_throughput":null,"throughput_provider":"DeepInfra","context_provider":"Fireworks"},{"rank":2,"model_id":"glm-5v-turbo","model_name":"GLM-5V-Turbo","organization_id":"zai-org","organization_name":"Zhipu AI","organization_country":"CN","score":0.75,"normalized_score":0.75,"verified":false,"self_reported":true,"self_reported_source":"https://docs.z.ai/guides/vlm/glm-5v-turbo","analysis_method":"Pass@3","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":"minimax-m3","model_name":"MiniMax M3","organization_id":"minimax","organization_name":"MiniMax","organization_country":"CN","score":0.745,"normalized_score":0.745,"verified":false,"self_reported":true,"self_reported_source":"https://www.minimax.io/blog/minimax-m3","analysis_method":"Pass^3","verification_date":null,"provider_id":"fireworks","input_cost_per_million":0.3,"output_cost_per_million":1.2,"context_window":1000000,"announcement_date":"2026-06-01","param_count":null,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Fireworks","best_throughput":null,"throughput_provider":"Fireworks","context_provider":"Novita"},{"rank":4,"model_id":"hy3","model_name":"Hy3","organization_id":"tencent","organization_name":"Tencent","organization_country":"CN","score":0.685,"normalized_score":0.685,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/tencent/Hy3","analysis_method":"pass^3","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-07-06","param_count":295000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":5,"model_id":"qwen3.7-max","model_name":"Qwen3.7 Max","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.652,"normalized_score":0.652,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.7","analysis_method":"Average","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":"Together"},{"rank":6,"model_id":"mimo-v2.5-pro","model_name":"MiMo-V2.5-Pro","organization_id":"xiaomi","organization_name":"Xiaomi","organization_country":"CN","score":0.64,"normalized_score":0.64,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5-Pro","analysis_method":"Hugging Face evaluation result, General","verification_date":null,"provider_id":"xiaomi","input_cost_per_million":0.435,"output_cost_per_million":0.87,"context_window":1048576,"announcement_date":"2026-04-27","param_count":1023244718976,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Xiaomi","best_throughput":null,"throughput_provider":"Xiaomi","context_provider":"Novita"},{"rank":7,"model_id":"mimo-v2.5","model_name":"MiMo-V2.5","organization_id":"xiaomi","organization_name":"Xiaomi","organization_country":"CN","score":0.632,"normalized_score":0.632,"verified":false,"self_reported":true,"self_reported_source":"https://mimo.xiaomi.com/mimo-v2-5/","analysis_method":"Multi Turn, Pass^3","verification_date":null,"provider_id":"novita","input_cost_per_million":0.168,"output_cost_per_million":0.336,"context_window":1048576,"announcement_date":"2026-04-22","param_count":310775040000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":"Novita","best_throughput":null,"throughput_provider":"Novita","context_provider":"Novita"},{"rank":8,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.627,"normalized_score":0.627,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.7-plus","analysis_method":null,"verification_date":null,"provider_id":"together","input_cost_per_million":0.32,"output_cost_per_million":1.28,"context_window":1000000,"announcement_date":"2026-05-31","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":9,"model_id":"mimo-v2-pro","model_name":"MiMo-V2-Pro","organization_id":"xiaomi","organization_name":"Xiaomi","organization_country":"CN","score":0.615,"normalized_score":0.615,"verified":false,"self_reported":true,"self_reported_source":"https://mimo.xiaomi.com/mimo-v2-pro","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-18","param_count":1000000000000,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":10,"model_id":"qwen3.6-27b","model_name":"Qwen3.6-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.606,"normalized_score":0.606,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-27b","analysis_method":"Pass^3","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":11,"model_id":"qwen3.6-plus","model_name":"Qwen3.6 Plus","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.587,"normalized_score":0.587,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6","analysis_method":"Pass^3","verification_date":null,"provider_id":"together","input_cost_per_million":0.5,"output_cost_per_million":3.0,"context_window":1000000,"announcement_date":"2026-04-02","param_count":null,"is_open_source":false,"is_new":false,"best_latency":null,"latency_provider":"Together","best_throughput":null,"throughput_provider":"Together","context_provider":"Together"},{"rank":12,"model_id":"mimo-v2-omni","model_name":"MiMo-V2-Omni","organization_id":"xiaomi","organization_name":"Xiaomi","organization_country":"CN","score":0.548,"normalized_score":0.548,"verified":false,"self_reported":true,"self_reported_source":"https://mimo.xiaomi.com/mimo-v2-omni","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-03-18","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":13,"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":0.5,"normalized_score":0.5,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.6-35b-a3b","analysis_method":"Pass^3","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}]}