# Logical Reasoning on FOLIO FOL fields (val)

Source: [Logical Reasoning on FOLIO FOL fields (val)](<https://www.sota2.com/research/sota/logical-reasoning-on-folio-fol-fields-val>)

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

Data updated: 2026-04-09T23:07:55.773Z

Evaluation of model performance on the Logical Reasoning task using the FOLIO FOL fields validation split, focusing on accuracy, epistemic uncertainty, and reasoning calls.

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 | Logical Reasoning |
| Dataset (including any stated split) | FOLIO FOL fields (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/logical-reasoning-on-folio-fol-fields-val.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Unknown Rate](<https://www.sota2.com/research/sota/logical-reasoning-on-folio-fol-fields-val.md?metric=Unknown%20Rate>): Higher is better; unit: PERCENT.

- [Epistemic Unknown Rate](<https://www.sota2.com/research/sota/logical-reasoning-on-folio-fol-fields-val.md?metric=Epistemic%20Unknown%20Rate>): Higher is better; unit: PERCENT.

- [Reasoning Calls](<https://www.sota2.com/research/sota/logical-reasoning-on-folio-fol-fields-val.md?metric=Reasoning%20Calls>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| CGD-PD | 68.1 | Not recorded | 69d732627d0172140ec76958 |
| GPT-5.2 (Single) | 63.7 | Not recorded | 69d732627d0172140ec76958 |
| CGD-PD | 49 | Not recorded | 69d732627d0172140ec76958 |
| Claude Sonnet 4.5 (Single) | 42.2 | Not recorded | 69d732627d0172140ec76958 |

### CGD-PD

Accuracy: 68.1. Result ID: 69d8312a47f34ce924bfd098.

[Reporting paper](<https://www.sota2.com/research/paper/69d732627d0172140ec76958.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d732627d0172140ec76958.md>)

Recorded evaluation configuration: {"Model":"GPT-5.2","Method":"CGD-PD"}. This record does not assert independent reproduction.

### GPT-5.2 (Single)

Accuracy: 63.7. Result ID: 69d8312a47f34ce924bfd097.

[Reporting paper](<https://www.sota2.com/research/paper/69d732627d0172140ec76958.md>)

Recorded evaluation configuration: {"Model":"GPT-5.2","Method":"Single"}. This record does not assert independent reproduction.

### CGD-PD

Accuracy: 49. Result ID: 69d8312a47f34ce924bfd09a.

[Reporting paper](<https://www.sota2.com/research/paper/69d732627d0172140ec76958.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69d732627d0172140ec76958.md>)

Recorded evaluation configuration: {"Model":"Claude Sonnet 4.5","Method":"CGD-PD"}. This record does not assert independent reproduction.

### Claude Sonnet 4.5 (Single)

Accuracy: 42.2. Result ID: 69d8312a47f34ce924bfd099.

[Reporting paper](<https://www.sota2.com/research/paper/69d732627d0172140ec76958.md>)

Recorded evaluation configuration: {"Model":"Claude Sonnet 4.5","Method":"Single"}. This record does not assert independent reproduction.

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