{"benchmark_id":"claw-eval-mm","benchmark_name":"ClawEval-MM","benchmark_description":"ClawEval-MM is the multimodal variant of ClawEval, evaluating agentic problem solving with visual inputs.","max_score":1.0,"categories":["multimodal","agents","vision"],"modality":"multimodal","total_models":5,"entries":[{"rank":1,"model_id":"qwen3.8-flash-next","model_name":"Qwen3.8-Flash-Next","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.604,"normalized_score":0.604,"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":"2026-08-26","announcement_date":"2026-08-26","multimodal":true,"param_count":125000000000,"is_new":true},{"rank":2,"model_id":"qwen3.8-27b","model_name":"Qwen3.8-27B","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.569,"normalized_score":0.569,"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":"2026-08-14","announcement_date":"2026-08-14","multimodal":true,"param_count":27781427952,"is_new":false},{"rank":3,"model_id":"qwen3.7-plus","model_name":"Qwen3.7-Plus","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.557,"normalized_score":0.557,"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":"2026-05-31","announcement_date":"2026-05-31","multimodal":true,"param_count":null,"is_new":false},{"rank":4,"model_id":"seed-2.1-pro","model_name":"Seed 2.1 Pro","organization_name":"ByteDance","organization_id":"bytedance","benchmark_score":0.51,"normalized_score":0.51,"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":5,"model_id":"seed-2.1-turbo","model_name":"Seed 2.1 Turbo","organization_name":"ByteDance","organization_id":"bytedance","benchmark_score":0.46,"normalized_score":0.46,"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}]}