BlogLLM Benchmark Scores as Published, Side by Side
Internal Research Debugging Evaluation: Results as Published
Every result the catalog holds for Internal Research Debugging Evaluation: 8 models from 1 developer, read from 3 pages. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area ML EngineeringMaintainer OpenAIIntroduced 2026Data version 2026103001, as of 2026-10-30
An internal OpenAI evaluation of debugging AI research systems, part of the suite OpenAI built from real AI research tasks (debugging research systems, optimizing kernels and training recipes, running machine learning experiments and improving another model) to measure how much a model accelerates its own development.
Internal Research Debugging Evaluation
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 76.39% | OpenAI, GPT-6.1 Terra system card addendumchecked 2026-10-26 | - |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 75.52% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 64.2% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-6 AstraOpenAI, released 2026-09-03 | 78.05% | OpenAI, GPT-6.1 Sol system card addendumchecked 2026-10-19 | - |
| GPT-5.6 LunaOpenAI, released 2026-07-09 | 50.8% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
| GPT-5.6 SolOpenAI, released 2026-07-09 | 68.3% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15; printed on 1 more page | - |
| GPT-5.6 TerraOpenAI, released 2026-07-09 | 67.8% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
| GPT-5.5OpenAI, released 2026-04-23 | 50% | OpenAI, GPT-5.6: Frontier intelligence that scales with your ambitionchecked 2026-10-15 | - |
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.