# Code Repair on R3

Source: [Code Repair on R3](<https://www.sota2.com/research/sota/code-repair-on-r3>)

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

Data updated: 2026-06-11T08:45:46.580Z

Evaluation of model performance on the Code Repair task using the R3 dataset, reporting ASR, D-1, D-2, and Time metrics.

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 | Code Repair |
| Dataset (including any stated split) | R3 |
| Metric | ASR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [ASR](<https://www.sota2.com/research/sota/code-repair-on-r3.md?metric=ASR>): Higher is better; unit: SCALAR.

- [D-1](<https://www.sota2.com/research/sota/code-repair-on-r3.md?metric=D-1>): Higher is better; unit: PERCENT.

- [D-2](<https://www.sota2.com/research/sota/code-repair-on-r3.md?metric=D-2>): Higher is better; unit: PERCENT.

- [Time](<https://www.sota2.com/research/sota/code-repair-on-r3.md?metric=Time>): Lower is better; unit: TIME.

## Recorded results

| Method | ASR | Result date | Report paper |
| --- | --- | --- | --- |
| EliBadCode | 1.92 | Not recorded | 6a28f37d90966ade919c1a11 |
| ScanNBT-NR | 1.91 | Not recorded | 6a28f37d90966ade919c1a11 |
| ScanNBT | 1.83 | Not recorded | 6a28f37d90966ade919c1a11 |

### EliBadCode

ASR: 1.92. Result ID: 6a2a74d1fbc373592c27a04f.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37d90966ade919c1a11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77101e209131cea70e2d.md>)

Recorded evaluation configuration: {"Backbone":"CodeBERT"}. This record does not assert independent reproduction.

### ScanNBT-NR

ASR: 1.91. Result ID: 6a2a74d1fbc373592c27a050.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37d90966ade919c1a11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f37d90966ade919c1a11.md>)

Recorded evaluation configuration: {"Backbone":"CodeBERT"}. This record does not assert independent reproduction.

### ScanNBT

ASR: 1.83. Result ID: 6a2a74d1fbc373592c27a051.

[Reporting paper](<https://www.sota2.com/research/paper/6a28f37d90966ade919c1a11.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a28f37d90966ade919c1a11.md>)

Recorded evaluation configuration: {"Backbone":"CodeBERT"}. This record does not assert independent reproduction.

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