# Propositional Logic Reasoning on ProsQA (val)

Source: [Propositional Logic Reasoning on ProsQA (val)](<https://www.sota2.com/research/sota/propositional-logic-reasoning-on-prosqa-val>)

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

Data updated: 2026-03-06T07:08:17.399Z

Evaluation of model performance on Propositional Logic Reasoning tasks using the validation split of the ProsQA dataset, 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 | Propositional Logic Reasoning |
| Dataset (including any stated split) | ProsQA (val) |
| 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/propositional-logic-reasoning-on-prosqa-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CoT2 | 93.37 | Not recorded | 68fa7ba21e209131cea89803 |
| COCONUT | 90.03 | Not recorded | 68fa7ba21e209131cea89803 |
| Discrete CoT | 68.5 | Not recorded | 68fa7ba21e209131cea89803 |
| Discrete no-CoT | 54.91 | Not recorded | 68fa7ba21e209131cea89803 |

### CoT2

Accuracy: 93.37. Result ID: 69aa7c3c6dbb7075b953ba4f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba21e209131cea89803.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ba21e209131cea89803.md>)

Recorded evaluation configuration: {"Backbone":"4-layer, 4-head GPT2 (d=32)","Budget":"Full"}. This record does not assert independent reproduction.

### COCONUT

Accuracy: 90.03. Result ID: 69aa7c3c6dbb7075b953ba50.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba21e209131cea89803.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa762f1e209131cea6bbb7.md>)

Recorded evaluation configuration: {"Backbone":"4-layer, 4-head GPT2 (d=32)"}. This record does not assert independent reproduction.

### Discrete CoT

Accuracy: 68.5. Result ID: 69aa7c3c6dbb7075b953ba51.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba21e209131cea89803.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e571e209131cea3f27b.md>)

Recorded evaluation configuration: {"Backbone":"4-layer, 4-head GPT2 (d=32)","Budget":"B=1"}. This record does not assert independent reproduction.

### Discrete no-CoT

Accuracy: 54.91. Result ID: 69aa7c3c6dbb7075b953ba52.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7ba21e209131cea89803.md>)

Recorded evaluation configuration: {"Backbone":"4-layer, 4-head GPT2 (d=32)"}. This record does not assert independent reproduction.

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