{"benchmark_id":"browsecomp-long-256k","name":"BrowseComp Long Context 256k","parent_benchmark":{"id":"browsecomp","name":"BrowseComp"},"categories":["reasoning","search"],"modality":"text","multilingual":false,"max_score":1.0,"language":"en","description":"BrowseComp is a benchmark for measuring the ability of agents to browse the web, comprising 1,266 questions that require persistently navigating the internet in search of hard-to-find, entangled information. Despite the difficulty of the questions, BrowseComp is simple and easy-to-use, as predicted answers are short and easily verifiable against reference answers. The benchmark focuses on questions where answers are obscure, time-invariant, and well-supported by evidence scattered across the open web.","paper_link":"https://arxiv.org/abs/2504.12516","implementation_link":null,"verified":false,"created_at":"2026-05-07T16:53:22.159408+00:00","updated_at":"2026-07-05T18:27:44.690723+00:00","statistics":{"total_models":2,"average_score":0.893,"min_score":0.888,"max_score":0.898,"score_stddev":0.007071067811865481,"verified_count":0,"self_reported_count":2},"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":0.898,"normalized_score":0.898,"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 256k.","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-5-2025-08-07","model_name":"GPT-5","organization_id":"openai","organization_name":"OpenAI","organization_country":"US","score":0.888,"normalized_score":0.888,"verified":false,"self_reported":true,"self_reported_source":"https://openai.com/index/introducing-gpt-5-for-developers/","analysis_method":"BrowseComp long-context 256k 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}]}