BlogLLM Benchmark Scores as Published, Side by Side
OpenAI Factuality on Flagged Conversations: Results as Published
Every result the catalog holds for OpenAI Factuality on Flagged Conversations: 3 models from 1 developer, read from 2 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 General Knowledge and ReasoningMaintainer OpenAIIntroduced 2026Data version 2026103001, as of 2026-10-30
This OpenAI factuality evaluation measures the share of answers that contain at least one factual error, on de-identified ChatGPT conversations where users had flagged a factual error from an earlier model. The prompts are deliberately difficult and not representative of typical usage, so the result is not a general error rate. The test set is internal to OpenAI, and lower is better.
Internal factuality evaluation (answers with at least one factual error)
lower is better
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPT-6.1 TerraOpenAI, released 2026-10-26 | 4.3% | OpenAI, GPT-6.1 Terrachecked 2026-10-26 | Model setup as reported: Maximum reasoning effort |
| 16.7% | OpenAI, GPT-6.1 Terrachecked 2026-10-26 | Model setup as reported: Low reasoning effort | |
| GPT-6.1 SolOpenAI, released 2026-09-29 | 7.7% | OpenAI, GPT-6.1 Solchecked 2026-10-14 | - |
| GPT-6 SolOpenAI, released 2026-09-22 | 11.4% | OpenAI, GPT-6.1 Solchecked 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.