BlogLLM Benchmark Scores as Published, Side by Side
OpenAI Internal Design Tasks: Results as Published
Every result the catalog holds for OpenAI Internal Design Tasks: 3 models from 2 developers, 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 Engineering and DesignMaintainer OpenAI (internal evaluation)Data version 2026103001, as of 2026-10-30
OpenAI's GPT-6 Astra launch page lists an internal Design Tasks evaluation in its benchmark charts, printing a score for each model, next to the public BenchCAD CAD benchmark. The page does not describe the tasks, the inputs or the scoring, and it does not state which direction is better. By its name the evaluation covers design work, but OpenAI has not confirmed what the tasks are.
Not checked against a maintainer's page.
Internal Design Tasks
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6 AstraOpenAI, released 2026-09-03 | 50% | OpenAI, GPT-6 Astrachecked 2026-10-14 | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 47.4% | OpenAI, GPT-6 Astrachecked 2026-10-14 | - |
| Claude Fable 5Anthropic, released 2026-06-09 | 35.8% | OpenAI, GPT-6 Astrachecked 2026-10-14 | - |
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.