PersonQA
Models answer questions about publicly available facts on people. Scored on accuracy, with hallucination rate reported alongside.
In-house OpenAI evaluation. Results here record accuracy and name the hallucination rate in the text.
- Made by
- OpenAI
- Released
- December 2024
- Kind
- Hallucination rates
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Short answer
- Tasks
- Kept private
- Strongest model tested
- o3 #83 on the capability index
- Last in a system card
- August 2025
- Last model added
- August 2025
ChatGPT agent leads with 94.3% among models released by August 2025
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.
The newest model with a score here came out in August 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 ChatGPT agent 94.3%
- 2 OpenAI deep research 86%
- 3 GPT-4.5 78%
- 4 o3 59%
- 5 o1 55%
- 6 o4-mini 36%
- 7 gpt-oss-120b 29.8%
- 8 o3-mini 21.7%
- 9 gpt-oss-20b 15.5%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | ChatGPT agent | 94.3% | Jul 2025 | Lab model card | |
| 2 | OpenAI deep research | 86% | Feb 2025 | Lab model card | |
| 3 | GPT-4.5 | 78% | Feb 2025 | Lab model card | |
| 4 | o3 | 59% | Apr 2025 | Lab model card | |
| 5 | o1 | 55% | Dec 2024 | Lab model card | |
| 6 | o4-mini | 36% | Apr 2025 | Lab model card | |
| 7 | gpt-oss-120b | 29.8% | Aug 2025 | Lab model card | |
| 8 | o3-mini | 21.7% | Jan 2025 | Lab model card | |
| 9 | gpt-oss-20b | 15.5% | Aug 2025 | Lab model card |
3 models have held number one in labs’ own numbers since its release in December 2024
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Labs’ model cards
OpenAI’s own number for OpenAI deep research passed 85% in February 2025
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Labs’ model cards
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
9 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 |
|---|---|---|---|---|
| Aug 5, 2025 | gpt-oss-20b model card | 15.5 | PersonQA, accuracy, no browsing (hallucination rate 53.2%) (Table 9) | Hallucination |
| Aug 5, 2025 | gpt-oss-120b model card | 29.8 | PersonQA, accuracy, no browsing (hallucination rate 49.1%) (Table 9) | Hallucination |
| Jul 17, 2025 | ChatGPT agent system card | 94.3 | PersonQA, accuracy, hallucination rate 0.043 (Table 4) | Hallucination |
| Apr 16, 2025 | o4-mini system card | 36 | PersonQA, accuracy, hallucination rate 0.48 (Table 4) | Hallucination |
| Apr 16, 2025 | o3 system card | 59 | PersonQA, accuracy, hallucination rate 0.33 (Table 4) | Hallucination |
| Feb 27, 2025 | GPT-4.5 system card | 78 | PersonQA, accuracy, hallucination rate 0.19 (Table 4) | Hallucination |
| Feb 25, 2025 | OpenAI deep research system card | 86 | PersonQA, accuracy 0.86, hallucination rate 0.13 (Table 11) | Hallucination |
| Jan 31, 2025 | o3-mini system card | 21.7 | PersonQA accuracy, hallucination rate 14.8% (Table 3) | Hallucination |
| Dec 5, 2024 | o1 system card | 55 | PersonQA, accuracy (hallucination rate 0.20) (Table 3) | 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%
- 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. GPT-6 Astra 4.20%
- Internal adversarially-designed factuality evaluations In use Models answer adversarial questions in nine categories such as history, math and code. Scored on agreement with human ideal responses. GPT-6 Luna 7.60%
- AA-Omniscience v1.1 In use Models answer 3,000 knowledge questions in six domains without tools and may abstain. The index adds correct answers and subtracts wrong ones.
Inkling 2 Small 16.1