# Psychological Profile Generation on Psy-Bench

Source: [Psychological Profile Generation on Psy-Bench](<https://www.sota2.com/research/sota/psychological-profile-generation-on-psy-bench>)

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

Data updated: 2026-04-14T08:41:36.387Z

Evaluation of models generating psychological profiles using the Psy-Bench dataset, assessed using SBERT, ROUGE-L, and BERTScore 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 | Psychological Profile Generation |
| Dataset (including any stated split) | Psy-Bench |
| Metric | SBERT Score |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [SBERT Score](<https://www.sota2.com/research/sota/psychological-profile-generation-on-psy-bench.md?metric=SBERT%20Score>): Higher is better; unit: SCALAR.

- [ROUGE-L Score](<https://www.sota2.com/research/sota/psychological-profile-generation-on-psy-bench.md?metric=ROUGE-L%20Score>): Higher is better; unit: SCALAR.

- [BERTScore F1](<https://www.sota2.com/research/sota/psychological-profile-generation-on-psy-bench.md?metric=BERTScore%20F1>): Higher is better; unit: SCALAR.

- [Average Score](<https://www.sota2.com/research/sota/psychological-profile-generation-on-psy-bench.md?metric=Average%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | SBERT Score | Result date | Report paper |
| --- | --- | --- | --- |
| StreamProfile (DeepSeek) | 0.68 | Not recorded | 69ddca327d0172140ec79b0b |
| StreamProfile (Qwen3) | 0.653 | Not recorded | 69ddca327d0172140ec79b0b |
| DeepSeek-V3 | 0.605 | Not recorded | 69ddca327d0172140ec79b0b |
| Qwen3-252B | 0.592 | Not recorded | 69ddca327d0172140ec79b0b |
| LLaMA-3.1-70B | 0.477 | Not recorded | 69ddca327d0172140ec79b0b |
| Qwen2-Audio | 0.323 | Not recorded | 69ddca327d0172140ec79b0b |

### StreamProfile (DeepSeek)

SBERT Score: 0.68. Result ID: 69ddfdbc47f34ce924c5790e.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca327d0172140ec79b0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca327d0172140ec79b0b.md>)

Recorded evaluation configuration: {"Model Type":"Text LLM","Reasoning Strategy":"StreamProfile","Backbone":"DeepSeek"}. This record does not assert independent reproduction.

### StreamProfile (Qwen3)

SBERT Score: 0.653. Result ID: 69ddfdbc47f34ce924c5790d.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca327d0172140ec79b0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69ddca327d0172140ec79b0b.md>)

Recorded evaluation configuration: {"Model Type":"Text LLM","Reasoning Strategy":"StreamProfile","Backbone":"Qwen3"}. This record does not assert independent reproduction.

### DeepSeek-V3

SBERT Score: 0.605. Result ID: 69ddfdbc47f34ce924c5790c.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca327d0172140ec79b0b.md>)

Recorded evaluation configuration: {"Model Type":"Text LLM","Reasoning Strategy":"No COT"}. This record does not assert independent reproduction.

### Qwen3-252B

SBERT Score: 0.592. Result ID: 69ddfdbc47f34ce924c5790a.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca327d0172140ec79b0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa788e1e209131cea79116.md>)

Recorded evaluation configuration: {"Model Type":"Text LLM","Reasoning Strategy":"No COT"}. This record does not assert independent reproduction.

### LLaMA-3.1-70B

SBERT Score: 0.477. Result ID: 69ddfdbc47f34ce924c5790b.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca327d0172140ec79b0b.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 Type":"Text LLM","Reasoning Strategy":"No COT"}. This record does not assert independent reproduction.

### Qwen2-Audio

SBERT Score: 0.323. Result ID: 69ddfdbc47f34ce924c57909.

[Reporting paper](<https://www.sota2.com/research/paper/69ddca327d0172140ec79b0b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74281e209131cea6017e.md>)

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

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