# Grammar Adaptation Similarity Comparison on EAST-ADL (train)

Source: [Grammar Adaptation Similarity Comparison on EAST-ADL (train)](<https://www.sota2.com/research/sota/grammar-adaptation-similarity-comparison-on-east-adl-train>)

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

Data updated: 2026-05-21T13:25:42.266Z

Evaluation of model performance on Grammar Adaptation Similarity Comparison using the training split of the EAST-ADL dataset, measured by similarity metrics like Same, Diff, and Percent.

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 | Grammar Adaptation Similarity Comparison |
| Dataset (including any stated split) | EAST-ADL (train) |
| Metric | Count (Same) |
| Unit | SCALAR |
| 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

- [Count (Same)](<https://www.sota2.com/research/sota/grammar-adaptation-similarity-comparison-on-east-adl-train.md?metric=Count%20(Same)>): Higher is better; unit: SCALAR.

- [Count (Different)](<https://www.sota2.com/research/sota/grammar-adaptation-similarity-comparison-on-east-adl-train.md?metric=Count%20(Different)>): Lower is better; unit: SCALAR.

- [Similarity Percent](<https://www.sota2.com/research/sota/grammar-adaptation-similarity-comparison-on-east-adl-train.md?metric=Similarity%20Percent>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Count (Same) | Result date | Report paper |
| --- | --- | --- | --- |
| Rule-based Approach | 297 | Not recorded | 6a0e91c8f984739ed6738e08 |
| Gemini-3-based Approach | 202 | Not recorded | 6a0e91c8f984739ed6738e08 |
| Claude-Sonnet-4.5-based Approach | 100 | Not recorded | 6a0e91c8f984739ed6738e08 |
| ChatGPT-5.1-based Approach | 1 | Not recorded | 6a0e91c8f984739ed6738e08 |

### Rule-based Approach

Count (Same): 297. Result ID: 6a0f071bfbc373592c07da2c.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91c8f984739ed6738e08.md>)

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

### Gemini-3-based Approach

Count (Same): 202. Result ID: 6a0f071bfbc373592c07da2b.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91c8f984739ed6738e08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0e91c8f984739ed6738e08.md>)

Recorded evaluation configuration: {"Model":"Gemini-3"}. This record does not assert independent reproduction.

### Claude-Sonnet-4.5-based Approach

Count (Same): 100. Result ID: 6a0f071bfbc373592c07da29.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91c8f984739ed6738e08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0e91c8f984739ed6738e08.md>)

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

### ChatGPT-5.1-based Approach

Count (Same): 1. Result ID: 6a0f071bfbc373592c07da2a.

[Reporting paper](<https://www.sota2.com/research/paper/6a0e91c8f984739ed6738e08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0e91c8f984739ed6738e08.md>)

Recorded evaluation configuration: {"Model":"ChatGPT-5.1"}. This record does not assert independent reproduction.

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