# Question Answering on TriviaQA (accuracy %)

Source: [Question Answering on TriviaQA (accuracy %)](<https://www.sota2.com/research/sota/question-answering-on-triviaqa-accuracy-percent>)

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

Data updated: 2026-04-29T08:33:21.192Z

Evaluation of model performance on the TriviaQA dataset for Question Answering, focusing specifically on the overall accuracy percentage metric.

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 | Question Answering |
| Dataset (including any stated split) | TriviaQA |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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/question-answering-on-triviaqa-accuracy-percent.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| SmolLM2 360M | 28 | Not recorded | 69f1906755a3c32af89fb8fa |
| Qwen2.5 0.5B | 27.8 | Not recorded | 69f1906755a3c32af89fb8fa |
| Granite 350M | 25.2 | Not recorded | 69f1906755a3c32af89fb8fa |
| Nautile-370M | 23.8 | Not recorded | 69f1906755a3c32af89fb8fa |
| LFM2.5 350M | 22.9 | Not recorded | 69f1906755a3c32af89fb8fa |

### SmolLM2 360M

Accuracy: 28. Result ID: 69f1c23947f34ce924d846ab.

[Reporting paper](<https://www.sota2.com/research/paper/69f1906755a3c32af89fb8fa.md>)

Recorded evaluation configuration: {"Training tokens":"4T","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction.

### Qwen2.5 0.5B

Accuracy: 27.8. Result ID: 69f1c23947f34ce924d846a8.

[Reporting paper](<https://www.sota2.com/research/paper/69f1906755a3c32af89fb8fa.md>)

Recorded evaluation configuration: {"Training tokens":"18T","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction.

### Granite 350M

Accuracy: 25.2. Result ID: 69f1c23947f34ce924d846a9.

[Reporting paper](<https://www.sota2.com/research/paper/69f1906755a3c32af89fb8fa.md>)

Recorded evaluation configuration: {"Training tokens":"10–12T","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction.

### Nautile-370M

Accuracy: 23.8. Result ID: 69f1c23947f34ce924d846a7.

[Reporting paper](<https://www.sota2.com/research/paper/69f1906755a3c32af89fb8fa.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69f1906755a3c32af89fb8fa.md>)

Recorded evaluation configuration: {"Training tokens":"∼0.8T","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction.

### LFM2.5 350M

Accuracy: 22.9. Result ID: 69f1c23947f34ce924d846aa.

[Reporting paper](<https://www.sota2.com/research/paper/69f1906755a3c32af89fb8fa.md>)

Recorded evaluation configuration: {"Training tokens":"28T","Evaluation Protocol":"0-shot"}. This record does not assert independent reproduction.

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