{"benchmark_id":"browsecomp-long-128k","name":"BrowseComp Long Context 128k","parent_benchmark":{"id":"browsecomp","name":"BrowseComp"},"categories":["reasoning","search"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"A challenging benchmark for evaluating web browsing agents' ability to persistently navigate the internet and find hard-to-locate, entangled information. Comprises 1,266 questions requiring strategic reasoning, creative search, and interpretation of retrieved content, with short and easily verifiable answers.","paper_link":"https://arxiv.org/abs/2504.12516","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:22.145938+00:00","updated_at":"2026-07-05T18:27:44.657166+00:00","statistics":{"total_models":5,"average_score":0.9040000000000001,"min_score":0.9,"max_score":0.92,"score_stddev":0.00894427190999913,"verified_count":0,"self_reported_count":5},"child_benchmarks":[],"linked_dataset":null,"models":[{"rank":1,"model_id":"gpt-5.2-2025-12-11","model_name":"GPT-5.2","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.92,"normalized_score":0.92,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-2/","analysis_method":"GPT-5.2 Thinking - BrowseComp Long Context 128k.","verification_date":null,"provider_id":"openai","input_cost_per_million":1.75,"output_cost_per_million":14.0,"context_window":400000,"announcement_date":"2025-12-11","param_count":null,"is_open_source":false,"is_new":false,"best_latency":2.0,"latency_provider":"OpenAI","best_throughput":100.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":2,"model_id":"gpt-5.1-2025-11-13","model_name":"GPT-5.1","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.9,"normalized_score":0.9,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-5-1/","analysis_method":"GPT-5.1 with adaptive reasoning - BrowseComp long-context 128k variant.","verification_date":null,"provider_id":"openai","input_cost_per_million":1.25,"output_cost_per_million":10.0,"context_window":400000,"announcement_date":"2025-11-13","param_count":null,"is_open_source":false,"is_new":false,"best_latency":2.0,"latency_provider":"OpenAI","best_throughput":100.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":2,"model_id":"gpt-5.1-instant-2025-11-12","model_name":"GPT-5.1 Instant","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.9,"normalized_score":0.9,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-5-1/","analysis_method":"GPT-5.1 with adaptive reasoning - BrowseComp long-context 128k variant.","verification_date":null,"provider_id":"openai","input_cost_per_million":1.25,"output_cost_per_million":10.0,"context_window":400000,"announcement_date":"2025-11-12","param_count":null,"is_open_source":false,"is_new":false,"best_latency":2.0,"latency_provider":"OpenAI","best_throughput":100.0,"throughput_provider":"OpenAI","context_provider":"OpenAI"},{"rank":2,"model_id":"gpt-5.1-thinking-2025-11-12","model_name":"GPT-5.1 Thinking","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.9,"normalized_score":0.9,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/gpt-5-1/","analysis_method":"GPT-5.1 Thinking with adaptive reasoning - BrowseComp long-context 128k variant.","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-11-12","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":2,"model_id":"gpt-5-2025-08-07","model_name":"GPT-5","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.9,"normalized_score":0.9,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-for-developers/","analysis_method":"BrowseComp long-context 128k variant.","verification_date":null,"provider_id":null,"input_cost_per_million":null,"output_cost_per_million":null,"context_window":null,"announcement_date":"2025-08-07","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}]}