# Science Question Answering on ARC (Accuracy, Reusability, Verifiability)

Source: [Science Question Answering on ARC (Accuracy, Reusability, Verifiability)](<https://www.sota2.com/research/sota/science-question-answering-on-arc-accuracy-reusability-verifiability>)

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

Data updated: 2026-02-26T05:33:10.078Z

Evaluation of model performance on the Abstract Reasoning Corpus (ARC) for Science Question Answering, reporting scores for Accuracy, Reusability, and Verifiability.

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 | Science Question Answering |
| Dataset (including any stated split) | ARC |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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/science-question-answering-on-arc-accuracy-reusability-verifiability.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Reusability](<https://www.sota2.com/research/sota/science-question-answering-on-arc-accuracy-reusability-verifiability.md?metric=Reusability>): Higher is better; unit: PERCENT.

- [Verifiability](<https://www.sota2.com/research/sota/science-question-answering-on-arc-accuracy-reusability-verifiability.md?metric=Verifiability>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| DeepSeek-R1 | 95 | Not recorded | 6997eabc09c33900fcd7678b |
| Gemma3 | 93 | Not recorded | 6997eabc09c33900fcd7678b |
| Llama3.1 | 83 | Not recorded | 6997eabc09c33900fcd7678b |
| Phi4-Reasoning | 81 | Not recorded | 6997eabc09c33900fcd7678b |

### DeepSeek-R1

Accuracy: 95. Result ID: 699b0e8c5698665ec4a1b1fb.

[Reporting paper](<https://www.sota2.com/research/paper/6997eabc09c33900fcd7678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Gemma3

Accuracy: 93. Result ID: 699b0e8c5698665ec4a1b1f8.

[Reporting paper](<https://www.sota2.com/research/paper/6997eabc09c33900fcd7678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Llama3.1

Accuracy: 83. Result ID: 699b0e8c5698665ec4a1b1f9.

[Reporting paper](<https://www.sota2.com/research/paper/6997eabc09c33900fcd7678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Phi4-Reasoning

Accuracy: 81. Result ID: 699b0e8c5698665ec4a1b1fa.

[Reporting paper](<https://www.sota2.com/research/paper/6997eabc09c33900fcd7678b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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