{"benchmark_id":"seal-0","name":"Seal-0","parent_benchmark":null,"categories":["reasoning","search"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"Seal-0 is a benchmark for evaluating agentic search capabilities, testing models' ability to navigate and retrieve information using tools.","paper_link":null,"implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:26.108393+00:00","updated_at":"2026-07-05T18:28:00.340737+00:00","statistics":{"total_models":6,"average_score":0.4888333333333333,"min_score":0.414,"max_score":0.574,"score_stddev":0.06529752420013081,"verified_count":0,"self_reported_count":6},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"kimi-k2.5","model_name":"Kimi K2.5","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.574,"normalized_score":0.574,"verified":false,"self_reported":true,"self_reported_source":"https://www.kimi.com/blog/kimi-k2-5.html","analysis_method":"Agents","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-01-27","param_count":1000000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":2,"model_id":"kimi-k2-thinking-0905","model_name":"Kimi K2-Thinking-0905","organization_id":"moonshotai","organization_name":"Moonshot AI","organization_country":"CN","score":0.563,"normalized_score":0.563,"verified":false,"self_reported":true,"self_reported_source":"https://huggingface.co/moonshotai/Kimi-K2-Thinking","analysis_method":"w/ tools","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-09-05","param_count":1000000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":3,"model_id":"qwen3.5-27b","model_name":"Qwen3.5-27B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.472,"normalized_score":0.472,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":"novita","input_cost_per_million":0.3,"output_cost_per_million":2.4,"context_window":262144,"announcement_date":"2026-02-24","param_count":27000000000,"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":"qwen3.5-397b-a17b","model_name":"Qwen3.5-397B-A17B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.469,"normalized_score":0.469,"verified":false,"self_reported":true,"self_reported_source":"https://qwenlm.github.io/blog/qwen3.5/","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-16","param_count":397000000000,"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":"qwen3.5-122b-a10b","model_name":"Qwen3.5-122B-A10B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.441,"normalized_score":0.441,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","param_count":122000000000,"is_open_source":true,"is_new":false,"best_latency":null,"latency_provider":null,"best_throughput":null,"throughput_provider":null,"context_provider":null},{"rank":6,"model_id":"qwen3.5-35b-a3b","model_name":"Qwen3.5-35B-A3B","organization_id":"qwen","organization_name":"Alibaba Cloud / Qwen Team","organization_country":"CN","score":0.414,"normalized_score":0.414,"verified":false,"self_reported":true,"self_reported_source":"https://qwen.ai/blog?id=qwen3.5","analysis_method":null,"verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2026-02-24","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}]}