GDPval: Results as Published

GDPval tests AI models on real deliverables from working professionals: tasks drawn from the work activities of 44 occupations across the nine sectors that contribute most to US GDP, written by people with about 14 years of experience in the job. Expert graders compare the model's deliverable with the human one, and the headline figure is the share of tasks where the model output wins or ties against the professional. A 220-task gold subset is open.

Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.