Factuality Heavy prompts
Models answer prompts representative of factuality-heavy ChatGPT conversations. A grader with web access counts responses and claims with factual errors.
In-house OpenAI evaluation. Error rates are not production prevalence.
- Level
- Everyday Most adults, without training
- Scored
- Graded by a model A language model scores each response, usually against a rubric.
- Answers
- Open-ended Free-form text, documents, designs or media judged as a whole.
GPT-6 Sol leads with 5.40%
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
- 1 GPT-6 Sol 5.40%
- 2 GPT-6 Luna 5.60%
- 3 GPT-5.5 Instant 17.9%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Sol | 5.40% | Oct 2026 | Model card | |
| 2 | GPT-6 Luna | 5.60% | Oct 2026 | Model card | |
| 3 | GPT-5.5 Instant | 17.9% | May 2026 | Model card |
2 models have held number one since its release in Aug 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
6 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| 29 Oct 2026 | GPT-6 Luna system card addendum | 8.5 | Factuality Heavy, responses with factual errors (claims with errors 2.5%), printed chart label (Figure 3) | Hallucination |
| 7 Oct 2026 | GPT-6 Sol system card addendum | 5.4 | Factuality Heavy, responses with factual errors (claims with errors 1.9%), printed chart label (Figure 3) | Hallucination |
| 7 Oct 2026 | GPT-6 Luna system card addendum | 5.6 | Factuality Heavy, responses with factual errors (claims with errors 1.6%), printed chart label (Figure 3) | Hallucination |
| 6 Aug 2026 | GPT-5.6 Sol system card addendum | 0.27 | Factuality Heavy, relative hallucination rate vs GPT-5.3 Instant, % responses with factual error, 0.27x, printed chart label (Figure 2, 6) | Hallucination |
| 6 Aug 2026 | GPT-5.6 Luna system card addendum | 0.47 | Factuality Heavy, relative hallucination rate vs GPT-5.3 Instant, % responses with factual error, 0.47x, printed chart label (Figure 2, 6) | Hallucination |
| 4 May 2026 | GPT-5.5 Instant system card | 17.9 | Factuality Heavy, responses with factual error (claims with factual error 4.4%), printed chart label (Figure 2) | Hallucination |
More in Factuality
- SimpleVQA In use Models answer 2,025 short factual questions about images across 9 tasks and 9 topics. An LLM judge grades answers against fixed references.
Qwen3.7-Plus 81.7% - HallusionBench In use Models answer 1,129 yes or no questions about 346 images, built in pairs to expose language hallucination and visual illusion. Scored by accuracy.
Keye-VL-2.0-30B-A3B 73.5% - SimpleQA Verified In use 1,000 human-verified, de-duplicated short-answer factual questions measuring parametric knowledge.
Gemini 3.1 Pro 77.5% - GaRAGe In use Models write long-form RAG answers to 2,366 questions with human-annotated grounding passages. Scoring checks whether answers use the relevant passages.
Nemotron 3.5 Bolt E4B 40.7% - Kimi Hallu Bench In use Models answer hard prompts drawn from practical work tasks. Fact-checking agents score the share of claims that are hallucinated. Kimi K3.1 Pro 8.30%
- RAGTruth In use A word-level annotated corpus of hallucinations in retrieval-augmented generation answers. It is used to train and evaluate hallucination detection and RAG faithfulness. Nemotron 3.5 Bolt E4B 77.9%