# Science Question Answering on ScienceQA (out-of-distribution)

Source: [Science Question Answering on ScienceQA (out-of-distribution)](<https://www.sota2.com/research/sota/science-question-answering-on-scienceqa-out-of-distribution>)

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

Data updated: 2026-02-26T05:33:23.839Z

Evaluation of model performance on the out-of-distribution subset of the ScienceQA dataset for Science Question Answering, measured by accuracy.

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) | ScienceQA (out-of-distribution) |
| Metric | Accuracy |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/science-question-answering-on-scienceqa-out-of-distribution.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CalibRL | 89.04 | Not recorded | 699e82056017c4460fface79 |
| GRPO | 88.34 | Not recorded | 699e82056017c4460fface79 |
| DAPO | 87.95 | Not recorded | 699e82056017c4460fface79 |
| LUFFY | 87.95 | Not recorded | 699e82056017c4460fface79 |
| RL-PLUS | 87.5 | Not recorded | 699e82056017c4460fface79 |
| SFT+GRPO | 86.36 | Not recorded | 699e82056017c4460fface79 |

### CalibRL

Accuracy: 89.04. Result ID: 699ea4cc5698665ec46fee46.

[Reporting paper](<https://www.sota2.com/research/paper/699e82056017c4460fface79.md>)

[Method origin paper](<https://www.sota2.com/research/paper/699e82056017c4460fface79.md>)

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

### GRPO

Accuracy: 88.34. Result ID: 699ea4cc5698665ec46fee41.

[Reporting paper](<https://www.sota2.com/research/paper/699e82056017c4460fface79.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73101e209131cea5a395.md>)

[Implementation](<https://github.com/deepseek-ai/DeepSeek-Math>)

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

### DAPO

Accuracy: 87.95. Result ID: 699ea4cc5698665ec46fee43.

[Reporting paper](<https://www.sota2.com/research/paper/699e82056017c4460fface79.md>)

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

### LUFFY

Accuracy: 87.95. Result ID: 699ea4cc5698665ec46fee44.

[Reporting paper](<https://www.sota2.com/research/paper/699e82056017c4460fface79.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79961e209131cea7e682.md>)

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

### RL-PLUS

Accuracy: 87.5. Result ID: 699ea4cc5698665ec46fee45.

[Reporting paper](<https://www.sota2.com/research/paper/699e82056017c4460fface79.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c411e209131cea8d325.md>)

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

### SFT+GRPO

Accuracy: 86.36. Result ID: 699ea4cc5698665ec46fee42.

[Reporting paper](<https://www.sota2.com/research/paper/699e82056017c4460fface79.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.