# Dimensional Aspect Sentiment Regression on JPN Finance

Source: [Dimensional Aspect Sentiment Regression on JPN Finance](<https://www.sota2.com/research/sota/dimensional-aspect-sentiment-regression-on-jpn-finance>)

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

Data updated: 2026-03-06T08:20:03.900Z

Evaluation of Dimensional Aspect Sentiment Regression performance on the JPN Finance dataset, measured using RMSE\_VA.

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 | Dimensional Aspect Sentiment Regression |
| Dataset (including any stated split) | JPN Finance |
| Metric | RMSE\_VA |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 8 of 8 |
| 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

- [RMSE\_VA](<https://www.sota2.com/research/sota/dimensional-aspect-sentiment-regression-on-jpn-finance.md?metric=RMSE_VA>): Lower is better; unit: SCALAR.

## Recorded results

| Method | RMSE\_VA | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-OSS 120B | 1.0188 | Not recorded | 69aa5f702d603e6de3e41801 |
| Kimi K2 Thinking | 1.6396 | Not recorded | 69aa5f702d603e6de3e41801 |
| Qwen 3 14B | 1.8964 | Not recorded | 69aa5f702d603e6de3e41801 |
| GPT-5 mini | 1.9243 | Not recorded | 69aa5f702d603e6de3e41801 |
| Mistral 3 14B | 2.07 | Not recorded | 69aa5f702d603e6de3e41801 |
| Kimi K2 Thinking | 2.3379 | Not recorded | 69aa5f702d603e6de3e41801 |
| Llama 3.3 70B | 2.4191 | Not recorded | 69aa5f702d603e6de3e41801 |
| GPT-5 mini | 2.676 | Not recorded | 69aa5f702d603e6de3e41801 |

### GPT-OSS 120B

RMSE\_VA: 1.0188. Result ID: 69aa8e306dbb7075b9543ed6.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e41801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802fcea8b01e76cc8e1794.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised Fine-Tuning","Model":"GPT-OSS 120B"}. This record does not assert independent reproduction.

### Kimi K2 Thinking

RMSE\_VA: 1.6396. Result ID: 69aa8e306dbb7075b9543ed2.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e41801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802fcea8b01e76cc8e1794.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"One-shot","Model":"Kimi K2 Thinking"}. This record does not assert independent reproduction.

### Qwen 3 14B

RMSE\_VA: 1.8964. Result ID: 69aa8e306dbb7075b9543ed3.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e41801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802fcea8b01e76cc8e1794.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised Fine-Tuning","Model":"Qwen 3 14B"}. This record does not assert independent reproduction.

### GPT-5 mini

RMSE\_VA: 1.9243. Result ID: 69aa8e306dbb7075b9543ed1.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e41801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802fcea8b01e76cc8e1794.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"One-shot","Model":"GPT-5 mini"}. This record does not assert independent reproduction.

### Mistral 3 14B

RMSE\_VA: 2.07. Result ID: 69aa8e306dbb7075b9543ed4.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e41801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802fcea8b01e76cc8e1794.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised Fine-Tuning","Model":"Mistral 3 14B"}. This record does not assert independent reproduction.

### Kimi K2 Thinking

RMSE\_VA: 2.3379. Result ID: 69aa8e306dbb7075b9543ed0.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e41801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802fcea8b01e76cc8e1794.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","Model":"Kimi K2 Thinking"}. This record does not assert independent reproduction.

### Llama 3.3 70B

RMSE\_VA: 2.4191. Result ID: 69aa8e306dbb7075b9543ed5.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e41801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802fcea8b01e76cc8e1794.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Supervised Fine-Tuning","Model":"Llama 3.3 70B"}. This record does not assert independent reproduction.

### GPT-5 mini

RMSE\_VA: 2.676. Result ID: 69aa8e306dbb7075b9543ecf.

[Reporting paper](<https://www.sota2.com/research/paper/69aa5f702d603e6de3e41801.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69802fcea8b01e76cc8e1794.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Zero-shot","Model":"GPT-5 mini"}. This record does not assert independent reproduction.

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