# Question Answering on ARC Challenge (Perf. and Sp.)

Source: [Question Answering on ARC Challenge (Perf. and Sp.)](<https://www.sota2.com/research/sota/question-answering-on-arc-challenge-perf-and-sp>)

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

Data updated: 2026-05-12T11:11:30.708Z

Evaluation of model performance on the ARC Challenge dataset for Question Answering, reporting 'Perf.' and 'Sp.' 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 | Question Answering |
| Dataset (including any stated split) | ARC Challenge |
| Metric | 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

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

- [Speed](<https://www.sota2.com/research/sota/question-answering-on-arc-challenge-perf-and-sp.md?metric=Speed>): Lower is better; unit: TIME.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Best Model | 83.1 | Not recorded | 69004e1e3ef7ccd74e5e2f24 |
| BSBA | 78.62 | Not recorded | 69004e1e3ef7ccd74e5e2f24 |
| Baseline | 78.2 | Not recorded | 69004e1e3ef7ccd74e5e2f24 |

### Best Model

Accuracy: 83.1. Result ID: 6a030ad447f34ce924e6bc3f.

[Reporting paper](<https://www.sota2.com/research/paper/69004e1e3ef7ccd74e5e2f24.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004e1e3ef7ccd74e5e2f24.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1 8B","Shots":"5-shot","#D":"3"}. This record does not assert independent reproduction.

### BSBA

Accuracy: 78.62. Result ID: 6a030ad447f34ce924e6bc40.

[Reporting paper](<https://www.sota2.com/research/paper/69004e1e3ef7ccd74e5e2f24.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69004e1e3ef7ccd74e5e2f24.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1 8B","Shots":"5-shot","#D":"9"}. This record does not assert independent reproduction.

### Baseline

Accuracy: 78.2. Result ID: 6a030ad447f34ce924e6bc3e.

[Reporting paper](<https://www.sota2.com/research/paper/69004e1e3ef7ccd74e5e2f24.md>)

Recorded evaluation configuration: {"Backbone":"LLaMA 3.1 8B","Shots":"5-shot"}. This record does not assert independent reproduction.

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