BlogLLM Benchmark Scores as Published, Side by Side
OpenAI economically important tasks: Results as Published
Every result the catalog holds for OpenAI economically important tasks: 3 models from 1 developer, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Knowledge WorkMaintainer OpenAIIntroduced 2025Data version 2026103001, as of 2026-10-30
An OpenAI internal evaluation of complex, economically valuable knowledge work across more than 40 occupations (law, logistics, sales, engineering and others), in which model outputs are compared against expert work; the chart prints wins and ties against the experts. It precedes the public GDPval release.
Not checked against a maintainer's page.
OpenAI economically important tasks (wins or ties against experts)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-5OpenAI, released 2025-08-07 | 47.1% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high |
| ChatGPT agentOpenAI, released 2025-07-17 | 43.5% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high |
| o3OpenAI, released 2025-04-16 | 33.5% | OpenAI, Introducing GPT-5checked 2026-10-15 | Effort: high |
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.