# Truthful Question Answering on TruthfulQA o=5 (f\_clean)

Source: [Truthful Question Answering on TruthfulQA o=5 (f\_clean)](<https://www.sota2.com/research/sota/truthful-question-answering-on-truthfulqa-o-5-f_clean>)

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

Data updated: 2026-02-26T05:34:15.604Z

Evaluation of model performance on the specific TruthfulQA configuration 'o=5 (f\_clean)' using exact, semantic-level, and domain-level accuracy metrics.

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 | Truthful Question Answering |
| Dataset (including any stated split) | TruthfulQA o=5 (f\_clean) |
| Metric | Accuracy (Exact) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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 (Exact)](<https://www.sota2.com/research/sota/truthful-question-answering-on-truthfulqa-o-5-f_clean.md?metric=Accuracy%20(Exact)>): Higher is better; unit: PERCENT.

- [Accuracy (Semantic-level)](<https://www.sota2.com/research/sota/truthful-question-answering-on-truthfulqa-o-5-f_clean.md?metric=Accuracy%20(Semantic-level)>): Higher is better; unit: PERCENT.

- [Accuracy (Domain-level)](<https://www.sota2.com/research/sota/truthful-question-answering-on-truthfulqa-o-5-f_clean.md?metric=Accuracy%20(Domain-level)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy (Exact) | Result date | Report paper |
| --- | --- | --- | --- |
| baseline | 55.5 | Not recorded | 6979980ea2b28e761d87cbce |
| baseline | 47.4 | Not recorded | 6979980ea2b28e761d87cbce |
| baseline | 28.7 | Not recorded | 6979980ea2b28e761d87cbce |

### baseline

Accuracy (Exact): 55.5. Result ID: 699669b45698665ec4b04a57.

[Reporting paper](<https://www.sota2.com/research/paper/6979980ea2b28e761d87cbce.md>)

Recorded evaluation configuration: {"Model":"Qwen 2.5","Access":"–"}. This record does not assert independent reproduction.

### baseline

Accuracy (Exact): 47.4. Result ID: 699669b45698665ec4b04a58.

[Reporting paper](<https://www.sota2.com/research/paper/6979980ea2b28e761d87cbce.md>)

Recorded evaluation configuration: {"Model":"LLaMA-3","Access":"–"}. This record does not assert independent reproduction.

### baseline

Accuracy (Exact): 28.7. Result ID: 699669b45698665ec4b04a56.

[Reporting paper](<https://www.sota2.com/research/paper/6979980ea2b28e761d87cbce.md>)

Recorded evaluation configuration: {"Model":"Mistral","Access":"–"}. This record does not assert independent reproduction.

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