# Question Answering on ARC-Challenge Spanish (test)

Source: [Question Answering on ARC-Challenge Spanish (test)](<https://www.sota2.com/research/sota/question-answering-on-arc-challenge-spanish-test>)

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

Data updated: 2026-04-23T10:55:26.042Z

Evaluation of model performance on the test split of the Spanish version of the ARC Challenge dataset, measured using normalized accuracy (acc\_norm).

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) | ARC-Challenge Spanish (test) |
| Metric | Normalized Accuracy |
| 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

- [Normalized Accuracy](<https://www.sota2.com/research/sota/question-answering-on-arc-challenge-spanish-test.md?metric=Normalized%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Normalized Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ML | 32.48 | Not recorded | 69e9a78a55a3c32af89f7037 |
| HQ | 30.77 | Not recorded | 69e9a78a55a3c32af89f7037 |
| No filtering | 29.91 | Not recorded | 69e9a78a55a3c32af89f7037 |

### ML

Normalized Accuracy: 32.48. Result ID: 69e9fa8247f34ce924d1faaf.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78a55a3c32af89f7037.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e9a78a55a3c32af89f7037.md>)

Recorded evaluation configuration: {"Filtering Strategy":"Multilingual (ML) classifier","Model size":"1B"}. This record does not assert independent reproduction.

### HQ

Normalized Accuracy: 30.77. Result ID: 69e9fa8247f34ce924d1faae.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78a55a3c32af89f7037.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77041e209131cea7081f.md>)

Recorded evaluation configuration: {"Filtering Strategy":"Monolingual high-quality (HQ)","Model size":"1B"}. This record does not assert independent reproduction.

### No filtering

Normalized Accuracy: 29.91. Result ID: 69e9fa8247f34ce924d1faad.

[Reporting paper](<https://www.sota2.com/research/paper/69e9a78a55a3c32af89f7037.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79a31e209131cea7e97f.md>)

Recorded evaluation configuration: {"Filtering Strategy":"None","Model size":"1B"}. This record does not assert independent reproduction.

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