# Paraphrase Semantic Similarity on Human Evaluation 300 samples (random sample)

Source: [Paraphrase Semantic Similarity on Human Evaluation 300 samples (random sample)](<https://www.sota2.com/research/sota/paraphrase-semantic-similarity-on-human-evaluation-300-samples-random-sample>)

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

Data updated: 2026-02-26T06:04:07.338Z

Human evaluation of paraphrase semantic similarity performance based on a random sample of 300 instances, reporting scores aggregated from three distinct human rating dimensions.

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 | Paraphrase Semantic Similarity |
| Dataset (including any stated split) | Human Evaluation 300 samples (random sample) |
| Metric | Score 3 |
| 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

- [Score 3](<https://www.sota2.com/research/sota/paraphrase-semantic-similarity-on-human-evaluation-300-samples-random-sample.md?metric=Score%203>): Higher is better; unit: PERCENT.

- [Score 2](<https://www.sota2.com/research/sota/paraphrase-semantic-similarity-on-human-evaluation-300-samples-random-sample.md?metric=Score%202>): Higher is better; unit: PERCENT.

- [Score 1](<https://www.sota2.com/research/sota/paraphrase-semantic-similarity-on-human-evaluation-300-samples-random-sample.md?metric=Score%201>): Higher is better; unit: PERCENT.

- [Average Score](<https://www.sota2.com/research/sota/paraphrase-semantic-similarity-on-human-evaluation-300-samples-random-sample.md?metric=Average%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Score 3 | Result date | Report paper |
| --- | --- | --- | --- |
| PARANMT | 28.7 | Not recorded | 68fa6f801e209131cea46051 |
| PARABANK1 | 26.8 | Not recorded | 68fa6f801e209131cea46051 |
| PARABANK2 | 26.8 | Not recorded | 68fa6f801e209131cea46051 |
| PARAAMR | 26.5 | Not recorded | 68fa6f801e209131cea46051 |

### PARANMT

Score 3: 28.7. Result ID: 6990dbca3a6c31484903d299.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa64401e209131cea0376d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PARABANK1

Score 3: 26.8. Result ID: 6990dbca3a6c31484903d29a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65501e209131cea0995d.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PARABANK2

Score 3: 26.8. Result ID: 6990dbca3a6c31484903d29b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46051.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### PARAAMR

Score 3: 26.5. Result ID: 6990dbca3a6c31484903d29c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f801e209131cea46051.md>)

[Implementation](<https://github.com/uclanlp/ParaAMR>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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