# Science Question Answering on ARC Easy (Score)

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

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

Data updated: 2026-04-01T08:30:16.752Z

Evaluation of model performance on the Easy subset of the Abstract Reasoning Corpus (ARC) using the reported 'Score' metric.

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 Easy |
| Metric | Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

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

## Recorded results

| Method | Score | Result date | Report paper |
| --- | --- | --- | --- |
| Nemotron-CC\_ASI+ | 78.59 | Not recorded | 69cca6cd0636e5bf4afcbe7c |
| Nemotron-CC\_ASI | 77.55 | Not recorded | 69cca6cd0636e5bf4afcbe7c |
| DCLM | 75.13 | Not recorded | 69cca6cd0636e5bf4afcbe7c |
| Nemotron-CC | 74.94 | Not recorded | 69cca6cd0636e5bf4afcbe7c |
| Ultra-Fineweb | 73.96 | Not recorded | 69cca6cd0636e5bf4afcbe7c |
| Fineweb-Edu | 73.39 | Not recorded | 69cca6cd0636e5bf4afcbe7c |

### Nemotron-CC\_ASI+

Score: 78.59. Result ID: 69ccd78947f34ce924b68235.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6cd0636e5bf4afcbe7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca6cd0636e5bf4afcbe7c.md>)

[Implementation](<https://github.com/GAIR-NLP/ASI-Evolve>)

Recorded evaluation configuration: {"Pre-training Curation Strategy":"AI Discovered","Model Parameters":"3B","Training Token Budget":"500B tokens"}. This record does not assert independent reproduction.

### Nemotron-CC\_ASI

Score: 77.55. Result ID: 69ccd78947f34ce924b68234.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6cd0636e5bf4afcbe7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca6cd0636e5bf4afcbe7c.md>)

[Implementation](<https://github.com/GAIR-NLP/ASI-Evolve>)

Recorded evaluation configuration: {"Pre-training Curation Strategy":"AI Discovered","Model Parameters":"3B","Training Token Budget":"500B tokens"}. This record does not assert independent reproduction.

### DCLM

Score: 75.13. Result ID: 69ccd78947f34ce924b68232.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6cd0636e5bf4afcbe7c.md>)

Recorded evaluation configuration: {"Pre-training Curation Strategy":"Human Discovered","Model Parameters":"3B","Training Token Budget":"500B tokens"}. This record does not assert independent reproduction.

### Nemotron-CC

Score: 74.94. Result ID: 69ccd78947f34ce924b68233.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6cd0636e5bf4afcbe7c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ad31e209131cea855ab.md>)

Recorded evaluation configuration: {"Pre-training Curation Strategy":"AI Discovered","Model Parameters":"3B","Training Token Budget":"500B tokens"}. This record does not assert independent reproduction.

### Ultra-Fineweb

Score: 73.96. Result ID: 69ccd78947f34ce924b68231.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6cd0636e5bf4afcbe7c.md>)

Recorded evaluation configuration: {"Pre-training Curation Strategy":"Human Discovered","Model Parameters":"3B","Training Token Budget":"500B tokens"}. This record does not assert independent reproduction.

### Fineweb-Edu

Score: 73.39. Result ID: 69ccd78947f34ce924b68230.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6cd0636e5bf4afcbe7c.md>)

Recorded evaluation configuration: {"Pre-training Curation Strategy":"Human Discovered","Model Parameters":"3B","Training Token Budget":"500B tokens"}. This record does not assert independent reproduction.

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