# Multiple-choice factual recall on POLYFACT Low

Source: [Multiple-choice factual recall on POLYFACT Low](<https://www.sota2.com/research/sota/multiple-choice-factual-recall-on-polyfact-low>)

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

Data updated: 2026-06-08T06:32:02.729Z

Evaluation of model performance on the POLYFACT Low dataset focusing on multiple-choice factual recall questions, 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 | Multiple-choice factual recall |
| Dataset (including any stated split) | POLYFACT Low |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 12 of 12 |
| 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/multiple-choice-factual-recall-on-polyfact-low.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| GRPO | 56.93 | Not recorded | 6a264c8590966ade919be956 |
| GRPO | 54.48 | Not recorded | 6a264c8590966ade919be956 |
| CPT + GRPO | 54.41 | Not recorded | 6a264c8590966ade919be956 |
| Baseline | 52.26 | Not recorded | 6a264c8590966ade919be956 |
| CPT + SFT | 52.02 | Not recorded | 6a264c8590966ade919be956 |
| CPT | 51.82 | Not recorded | 6a264c8590966ade919be956 |
| Baseline | 51.8 | Not recorded | 6a264c8590966ade919be956 |
| CPT | 51.09 | Not recorded | 6a264c8590966ade919be956 |
| SFT | 50.04 | Not recorded | 6a264c8590966ade919be956 |
| CPT + GRPO | 49.33 | Not recorded | 6a264c8590966ade919be956 |
| SFT | 48.88 | Not recorded | 6a264c8590966ade919be956 |
| CPT + SFT | 47.53 | Not recorded | 6a264c8590966ade919be956 |

### GRPO

Accuracy: 56.93. Result ID: 6a266179fbc373592c226c42.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction.

### GRPO

Accuracy: 54.48. Result ID: 6a266179fbc373592c226c3c.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction.

### CPT + GRPO

Accuracy: 54.41. Result ID: 6a266179fbc373592c226c3d.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction.

### Baseline

Accuracy: 52.26. Result ID: 6a266179fbc373592c226c3e.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction.

### CPT + SFT

Accuracy: 52.02. Result ID: 6a266179fbc373592c226c3b.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction.

### CPT

Accuracy: 51.82. Result ID: 6a266179fbc373592c226c39.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction.

### Baseline

Accuracy: 51.8. Result ID: 6a266179fbc373592c226c38.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction.

### CPT

Accuracy: 51.09. Result ID: 6a266179fbc373592c226c3f.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction.

### SFT

Accuracy: 50.04. Result ID: 6a266179fbc373592c226c3a.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"OLMo-2-1124-7B"}. This record does not assert independent reproduction.

### CPT + GRPO

Accuracy: 49.33. Result ID: 6a266179fbc373592c226c43.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction.

### SFT

Accuracy: 48.88. Result ID: 6a266179fbc373592c226c40.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction.

### CPT + SFT

Accuracy: 47.53. Result ID: 6a266179fbc373592c226c41.

[Reporting paper](<https://www.sota2.com/research/paper/6a264c8590966ade919be956.md>)

Recorded evaluation configuration: {"Backbone":"Qwen-2.5-7B"}. This record does not assert independent reproduction.

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