{"benchmark_id":"wildclawbench","benchmark_name":"WildClawBench","benchmark_description":"WildClawBench is an agentic coding benchmark from InternLM/Claw-Eval that reports overall model performance on real-world tool-using development tasks.","max_score":1.0,"categories":["agents","coding"],"modality":"text","total_models":5,"entries":[{"rank":1,"model_id":"seed-2.1-turbo","model_name":"Seed 2.1 Turbo","organization_name":"ByteDance","organization_id":"bytedance","benchmark_score":0.628,"normalized_score":0.628,"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":"2026-06-24","announcement_date":"2026-06-24","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"seed-2.1-pro","model_name":"Seed 2.1 Pro","organization_name":"ByteDance","organization_id":"bytedance","benchmark_score":0.617,"normalized_score":0.617,"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":"2026-06-24","announcement_date":"2026-06-24","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"hy3","model_name":"Hy3","organization_name":"Tencent","organization_id":"tencent","benchmark_score":0.536,"normalized_score":0.536,"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":"2026-07-06","announcement_date":"2026-07-06","multimodal":false,"param_count":295000000000,"is_new":false},{"rank":4,"model_id":"muse-glimmer-30b","model_name":"Muse Glimmer-30B","organization_name":"Meta","organization_id":"meta","benchmark_score":0.476,"normalized_score":0.476,"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":"2026-08-10","announcement_date":"2026-08-10","multimodal":true,"param_count":29600000000,"is_new":false},{"rank":5,"model_id":"mimo-v2.5-pro","model_name":"MiMo-V2.5-Pro","organization_name":"Xiaomi","organization_id":"xiaomi","benchmark_score":0.43,"normalized_score":0.43,"verified":false,"self_reported":true,"provider_id":"xiaomi","input_cost_per_million":0.435,"output_cost_per_million":0.87,"speed_rps":null,"context_window":1048576,"release_date":"2026-04-27","announcement_date":"2026-04-27","multimodal":false,"param_count":1023244718976,"is_new":false}]}