# AST evaluation on Seal-Tools

Source: [AST evaluation on Seal-Tools](<https://www.sota2.com/research/sota/ast-evaluation-on-seal-tools>)

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

Data updated: 2026-06-16T09:58:01.873Z

Evaluation of model performance on Abstract Syntax Tree (AST) related metrics using the Seal-Tools dataset.

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 | AST evaluation |
| Dataset (including any stated split) | Seal-Tools |
| Metric | Free Name Score |
| 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

- [Free Name Score](<https://www.sota2.com/research/sota/ast-evaluation-on-seal-tools.md?metric=Free%20Name%20Score>): Higher is better; unit: PERCENT.

- [Free AST Score](<https://www.sota2.com/research/sota/ast-evaluation-on-seal-tools.md?metric=Free%20AST%20Score>): Higher is better; unit: PERCENT.

- [Forced-Base AST Score](<https://www.sota2.com/research/sota/ast-evaluation-on-seal-tools.md?metric=Forced-Base%20AST%20Score>): Higher is better; unit: PERCENT.

- [Gated AST Score](<https://www.sota2.com/research/sota/ast-evaluation-on-seal-tools.md?metric=Gated%20AST%20Score>): Higher is better; unit: PERCENT.

- [Gold Ceiling Score](<https://www.sota2.com/research/sota/ast-evaluation-on-seal-tools.md?metric=Gold%20Ceiling%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Free Name Score | Result date | Report paper |
| --- | --- | --- | --- |
| Llama-3.1-8B | 94.2 | Not recorded | 6a30d90ad33dfb23e783d1fc |
| Qwen2.5-7B | 92.9 | Not recorded | 6a30d90ad33dfb23e783d1fc |
| Pooled | 92.1 | Not recorded | 6a30d90ad33dfb23e783d1fc |
| Qwen2.5-1.5B | 89.1 | Not recorded | 6a30d90ad33dfb23e783d1fc |

### Llama-3.1-8B

Free Name Score: 94.2. Result ID: 6a311e14fbc373592c2df901.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d90ad33dfb23e783d1fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d90ad33dfb23e783d1fc.md>)

Recorded evaluation configuration: {"Model":"Llama-3.1-8B"}. This record does not assert independent reproduction.

### Qwen2.5-7B

Free Name Score: 92.9. Result ID: 6a311e14fbc373592c2df900.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d90ad33dfb23e783d1fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d90ad33dfb23e783d1fc.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-7B"}. This record does not assert independent reproduction.

### Pooled

Free Name Score: 92.1. Result ID: 6a311e14fbc373592c2df902.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d90ad33dfb23e783d1fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d90ad33dfb23e783d1fc.md>)

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

### Qwen2.5-1.5B

Free Name Score: 89.1. Result ID: 6a311e14fbc373592c2df8ff.

[Reporting paper](<https://www.sota2.com/research/paper/6a30d90ad33dfb23e783d1fc.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a30d90ad33dfb23e783d1fc.md>)

Recorded evaluation configuration: {"Model":"Qwen2.5-1.5B"}. This record does not assert independent reproduction.

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