# Science Question Answering on ARC (Performance)

Source: [Science Question Answering on ARC (Performance)](<https://www.sota2.com/research/sota/science-question-answering-on-arc-performance>)

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

Data updated: 2026-03-10T12:39:14.223Z

Evaluation of model performance on the Abstract Reasoning Corpus (ARC) for Science Question Answering, reporting a metric specifically labeled 'Performance'.

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 | Performance |
| 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

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

## Recorded results

| Method | Performance | Result date | Report paper |
| --- | --- | --- | --- |
| AutoAdapt | 90.87 | Not recorded | 69afa5b92d603e6de3e43e35 |
| AutoMLAgent | 76.71 | Not recorded | 69afa5b92d603e6de3e43e35 |
| MLCopilot | 28.84 | Not recorded | 69afa5b92d603e6de3e43e35 |
| DS-Agent | 14.85 | Not recorded | 69afa5b92d603e6de3e43e35 |

### AutoAdapt

Performance: 90.87. Result ID: 69b010de6dbb7075b959f439.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b92d603e6de3e43e35.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69afa5b92d603e6de3e43e35.md>)

Recorded evaluation configuration: {"setting":"Template Free (TF)"}. This record does not assert independent reproduction.

### AutoMLAgent

Performance: 76.71. Result ID: 69b010de6dbb7075b959f43a.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b92d603e6de3e43e35.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79281e209131cea7c4c9.md>)

Recorded evaluation configuration: {"setting":"Template Free (TF)"}. This record does not assert independent reproduction.

### MLCopilot

Performance: 28.84. Result ID: 69b010de6dbb7075b959f43b.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b92d603e6de3e43e35.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72381e209131cea55046.md>)

[Implementation](<https://platform.openai.com/docs/models/gpt-3-5>)

Recorded evaluation configuration: {"setting":"Template Free (TF)"}. This record does not assert independent reproduction.

### DS-Agent

Performance: 14.85. Result ID: 69b010de6dbb7075b959f43c.

[Reporting paper](<https://www.sota2.com/research/paper/69afa5b92d603e6de3e43e35.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73601e209131cea5c01c.md>)

Recorded evaluation configuration: {"setting":"Template Free (TF)"}. This record does not assert independent reproduction.

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