# Prompt Classification on SEval

Source: [Prompt Classification on SEval](<https://www.sota2.com/research/sota/prompt-classification-on-seval>)

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

Data updated: 2026-02-26T05:43:31.944Z

Evaluation of model performance on the SEval dataset for Prompt Classification, measured by F1 score.

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 | Prompt classification |
| Dataset (including any stated split) | SEval |
| Metric | F1 Score |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 16 of 16 |
| 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

- [F1 Score](<https://www.sota2.com/research/sota/prompt-classification-on-seval.md?metric=F1%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | F1 Score | Result date | Report paper |
| --- | --- | --- | --- |
| YuFeng-XGuard | 92.5 | Not recorded | 69730068b2be0ed85a78c8a4 |
| YuFeng-XGuard | 91.7 | Not recorded | 69730068b2be0ed85a78c8a4 |
| Qwen3Guard-Gen | 87 | Not recorded | 69730068b2be0ed85a78c8a4 |
| Qwen3Guard-Gen | 86.6 | Not recorded | 69730068b2be0ed85a78c8a4 |
| PolyGuard | 86.3 | Not recorded | 69730068b2be0ed85a78c8a4 |
| GPT-OSS-SafeGuard | 85.4 | Not recorded | 69730068b2be0ed85a78c8a4 |
| Qwen3Guard-Gen | 85.1 | Not recorded | 69730068b2be0ed85a78c8a4 |
| NemotronReasoning | 83.5 | Not recorded | 69730068b2be0ed85a78c8a4 |
| WildGuard | 79.8 | Not recorded | 69730068b2be0ed85a78c8a4 |
| NemotronGuardV2 | 77.7 | Not recorded | 69730068b2be0ed85a78c8a4 |
| Qwen3Guard-Gen | 74.6 | Not recorded | 69730068b2be0ed85a78c8a4 |
| Qwen3Guard-Gen | 73.2 | Not recorded | 69730068b2be0ed85a78c8a4 |
| Qwen3Guard-Gen | 72.7 | Not recorded | 69730068b2be0ed85a78c8a4 |
| Llama3Guard | 68 | Not recorded | 69730068b2be0ed85a78c8a4 |
| Llama4Guard | 60.4 | Not recorded | 69730068b2be0ed85a78c8a4 |
| ShieldGemma | 57.1 | Not recorded | 69730068b2be0ed85a78c8a4 |

### YuFeng-XGuard

F1 Score: 92.5. Result ID: 699675a75698665ec4bd1e31.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

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

### YuFeng-XGuard

F1 Score: 91.7. Result ID: 699675a75698665ec4bd1e27.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

Recorded evaluation configuration: {"Model Size":"0.6B"}. This record does not assert independent reproduction.

### Qwen3Guard-Gen

F1 Score: 87. Result ID: 699675a75698665ec4bd1e26.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c351e209131cea8d09c.md>)

Recorded evaluation configuration: {"Model Size":"4B","Evaluation protocol":"strict"}. This record does not assert independent reproduction.

### Qwen3Guard-Gen

F1 Score: 86.6. Result ID: 699675a75698665ec4bd1e30.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c351e209131cea8d09c.md>)

Recorded evaluation configuration: {"Model Size":"8B","Evaluation protocol":"strict"}. This record does not assert independent reproduction.

### PolyGuard

F1 Score: 86.3. Result ID: 699675a75698665ec4bd1e2d.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a751e209131cea835e9.md>)

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

### GPT-OSS-SafeGuard

F1 Score: 85.4. Result ID: 699675a75698665ec4bd1e2e.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a0c.md>)

Recorded evaluation configuration: {"Model Size":"20B"}. This record does not assert independent reproduction.

### Qwen3Guard-Gen

F1 Score: 85.1. Result ID: 699675a75698665ec4bd1e23.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c351e209131cea8d09c.md>)

Recorded evaluation configuration: {"Model Size":"0.6B","Evaluation protocol":"strict"}. This record does not assert independent reproduction.

### NemotronReasoning

F1 Score: 83.5. Result ID: 699675a75698665ec4bd1e24.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78d41e209131cea7aa41.md>)

Recorded evaluation configuration: {"Model Size":"4B"}. This record does not assert independent reproduction.

### WildGuard

F1 Score: 79.8. Result ID: 699675a75698665ec4bd1e2a.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76291e209131cea6b9a6.md>)

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

### NemotronGuardV2

F1 Score: 77.7. Result ID: 699675a75698665ec4bd1e2c.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa769b1e209131cea6e172.md>)

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

### Qwen3Guard-Gen

F1 Score: 74.6. Result ID: 699675a75698665ec4bd1e22.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c351e209131cea8d09c.md>)

Recorded evaluation configuration: {"Model Size":"0.6B","Evaluation protocol":"loose"}. This record does not assert independent reproduction.

### Qwen3Guard-Gen

F1 Score: 73.2. Result ID: 699675a75698665ec4bd1e25.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c351e209131cea8d09c.md>)

Recorded evaluation configuration: {"Model Size":"4B","Evaluation protocol":"loose"}. This record does not assert independent reproduction.

### Qwen3Guard-Gen

F1 Score: 72.7. Result ID: 699675a75698665ec4bd1e2f.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7c351e209131cea8d09c.md>)

Recorded evaluation configuration: {"Model Size":"8B","Evaluation protocol":"loose"}. This record does not assert independent reproduction.

### Llama3Guard

F1 Score: 68. Result ID: 699675a75698665ec4bd1e28.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

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

### Llama4Guard

F1 Score: 60.4. Result ID: 699675a75698665ec4bd1e29.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"Model Size":"12B"}. This record does not assert independent reproduction.

### ShieldGemma

F1 Score: 57.1. Result ID: 699675a75698665ec4bd1e2b.

[Reporting paper](<https://www.sota2.com/research/paper/69730068b2be0ed85a78c8a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74661e209131cea617ba.md>)

Recorded evaluation configuration: {"Model Size":"9B"}. This record does not assert independent reproduction.

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