# Fact-seeking Question Answering on SimpleQA no web

Source: [Fact-seeking Question Answering on SimpleQA no web](<https://www.sota2.com/research/sota/fact-seeking-question-answering-on-simpleqa-no-web>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:31:09.298Z

Evaluation of model performance on the SimpleQA no web dataset for Fact-seeking Question Answering, measured using accuracy and hallucination rate.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Fact-seeking Question Answering |
| Dataset (including any stated split) | SimpleQA no web |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Accuracy](<https://www.sota2.com/research/sota/fact-seeking-question-answering-on-simpleqa-no-web.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Hallucination Rate](<https://www.sota2.com/research/sota/fact-seeking-question-answering-on-simpleqa-no-web.md?metric=Hallucination%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| gpt-5-thinking | 55 | Not recorded | 695f39f053fdd5c361743ecb |
| OpenAI o3 | 54 | Not recorded | 695f39f053fdd5c361743ecb |
| gpt-5-main | 46 | Not recorded | 695f39f053fdd5c361743ecb |
| GPT-4o | 44 | Not recorded | 695f39f053fdd5c361743ecb |
| OpenAI o4-mini | 24 | Not recorded | 695f39f053fdd5c361743ecb |
| gpt-5-thinking-mini | 22 | Not recorded | 695f39f053fdd5c361743ecb |
| gpt-5-thinking-nano | 11 | Not recorded | 695f39f053fdd5c361743ecb |

### gpt-5-thinking

Accuracy: 55. Result ID: 6996b8e75698665ec40392fd.

[Reporting paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Browsing setting":"disabled"}. This record does not assert independent reproduction.

### OpenAI o3

Accuracy: 54. Result ID: 6996b8e75698665ec40392fe.

[Reporting paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Browsing setting":"disabled"}. This record does not assert independent reproduction.

### gpt-5-main

Accuracy: 46. Result ID: 6996b8e75698665ec4039302.

[Reporting paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Browsing setting":"disabled"}. This record does not assert independent reproduction.

### GPT-4o

Accuracy: 44. Result ID: 6996b8e75698665ec4039303.

[Reporting paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Browsing setting":"disabled"}. This record does not assert independent reproduction.

### OpenAI o4-mini

Accuracy: 24. Result ID: 6996b8e75698665ec4039300.

[Reporting paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Browsing setting":"disabled"}. This record does not assert independent reproduction.

### gpt-5-thinking-mini

Accuracy: 22. Result ID: 6996b8e75698665ec40392ff.

[Reporting paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Browsing setting":"disabled"}. This record does not assert independent reproduction.

### gpt-5-thinking-nano

Accuracy: 11. Result ID: 6996b8e75698665ec4039301.

[Reporting paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/695f39f053fdd5c361743ecb.md>)

Recorded evaluation configuration: {"Browsing setting":"disabled"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.