# Human Evaluation of Personality Expression on BIG5-CHAT (test)

Source: [Human Evaluation of Personality Expression on BIG5-CHAT (test)](<https://www.sota2.com/research/sota/human-evaluation-of-personality-expression-on-big5-chat-test>)

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

Data updated: 2026-02-26T06:08:50.701Z

Subjective human evaluation comparing model outputs on the BIG5-CHAT test set, assessing personality expression via pairwise comparisons (win/loss/draw) and Cohen's Kappa agreement.

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 | Human Evaluation of Personality Expression |
| Dataset (including any stated split) | BIG5-CHAT (test) |
| Metric | Win Rate |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| 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

- [Win Rate](<https://www.sota2.com/research/sota/human-evaluation-of-personality-expression-on-big5-chat-test.md?metric=Win%20Rate>): Higher is better; unit: PERCENT.

- [Draw Rate](<https://www.sota2.com/research/sota/human-evaluation-of-personality-expression-on-big5-chat-test.md?metric=Draw%20Rate>): Higher is better; unit: PERCENT.

- [Loss Rate](<https://www.sota2.com/research/sota/human-evaluation-of-personality-expression-on-big5-chat-test.md?metric=Loss%20Rate>): Lower is better; unit: PERCENT.

- [Cohen's Kappa](<https://www.sota2.com/research/sota/human-evaluation-of-personality-expression-on-big5-chat-test.md?metric=Cohen%27s%20Kappa>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Win Rate | Result date | Report paper |
| --- | --- | --- | --- |
| BIG5-CHAT | 50.2 | Not recorded | 68fa7a4c1e209131cea82495 |
| BIG5-CHAT | 47.8 | Not recorded | 68fa7a4c1e209131cea82495 |

### BIG5-CHAT

Win Rate: 50.2. Result ID: 698b73567a967eddb76eb31c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4c1e209131cea82495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4c1e209131cea82495.md>)

[Implementation](<https://github.com/jiarui-liu/Big5Chat>)

Recorded evaluation configuration: {"Evaluation Criterion":"Expressiveness"}. This record does not assert independent reproduction.

### BIG5-CHAT

Win Rate: 47.8. Result ID: 698b73567a967eddb76eb31d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a4c1e209131cea82495.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a4c1e209131cea82495.md>)

[Implementation](<https://github.com/jiarui-liu/Big5Chat>)

Recorded evaluation configuration: {"Evaluation Criterion":"Realism"}. This record does not assert independent reproduction.

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