# Question Answering on ARC Challenge DE (with Efficiency Metrics)

Source: [Question Answering on ARC Challenge DE (with Efficiency Metrics)](<https://www.sota2.com/research/sota/question-answering-on-arc-challenge-de-with-efficiency-metrics>)

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

Data updated: 2026-03-18T07:37:15.742Z

Evaluation of model performance on the ARC Challenge DE dataset for Question Answering, measured using Normalized Log Accuracy and sequence efficiency (bytes per sequence position).

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 DE |
| Metric | Normalized Log Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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 Log Accuracy](<https://www.sota2.com/research/sota/question-answering-on-arc-challenge-de-with-efficiency-metrics.md?metric=Normalized%20Log%20Accuracy>): Higher is better; unit: PERCENT.

- [Bytes per Sequence Position](<https://www.sota2.com/research/sota/question-answering-on-arc-challenge-de-with-efficiency-metrics.md?metric=Bytes%20per%20Sequence%20Position>): Lower is better; unit: SIZE.

## Recorded results

| Method | Normalized Log Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| HATified | 57.2 | Not recorded | 69ba317b0636e5bf4afc071d |
| Tülu | 33.6 | Not recorded | 69ba317b0636e5bf4afc071d |

### HATified

Normalized Log Accuracy: 57.2. Result ID: 69ba561247f34ce924a3d9a4.

[Reporting paper](<https://www.sota2.com/research/paper/69ba317b0636e5bf4afc071d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ba317b0636e5bf4afc071d.md>)

Recorded evaluation configuration: {"training":"SFT","shots":"25-shot"}. This record does not assert independent reproduction.

### Tülu

Normalized Log Accuracy: 33.6. Result ID: 69ba561247f34ce924a3d9a5.

[Reporting paper](<https://www.sota2.com/research/paper/69ba317b0636e5bf4afc071d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78121e209131cea76a04.md>)

Recorded evaluation configuration: {"training":"SFT","shots":"25-shot"}. This record does not assert independent reproduction.

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