# NLG Meta-evaluation on CUS-QA orig. (sk)

Source: [NLG Meta-evaluation on CUS-QA orig. (sk)](<https://www.sota2.com/research/sota/nlg-meta-evaluation-on-cus-qa-orig-sk>)

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

Data updated: 2026-03-11T08:42:18.133Z

Evaluation of Natural Language Generation (NLG) Meta-evaluation performance on the CUS-QA orig. (sk) dataset, measured using Kendall correlation.

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 | NLG Meta-evaluation |
| Dataset (including any stated split) | CUS-QA orig. (sk) |
| Metric | Kendall Correlation |
| 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

- [Kendall Correlation](<https://www.sota2.com/research/sota/nlg-meta-evaluation-on-cus-qa-orig-sk.md?metric=Kendall%20Correlation>): Higher is better; unit: SCALAR.

## Recorded results

| Method | Kendall Correlation | Result date | Report paper |
| --- | --- | --- | --- |
| Qwen 3 30B | 0.788 | Not recorded | 69b0f7292d603e6de3e45f20 |
| Llama 4 Scout | 0.735 | Not recorded | 69b0f7292d603e6de3e45f20 |
| Llama 3.3 70B | 0.73 | Not recorded | 69b0f7292d603e6de3e45f20 |
| Qwen 3 30B | 0.709 | Not recorded | 69b0f7292d603e6de3e45f20 |
| Llama 4 Scout | 0.704 | Not recorded | 69b0f7292d603e6de3e45f20 |
| Llama 3.3 70B | 0.656 | Not recorded | 69b0f7292d603e6de3e45f20 |

### Qwen 3 30B

Kendall Correlation: 0.788. Result ID: 69b12ae56dbb7075b95b9dda.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

Recorded evaluation configuration: {"Shot":"Zero"}. This record does not assert independent reproduction.

### Llama 4 Scout

Kendall Correlation: 0.735. Result ID: 69b12ae56dbb7075b95b9dd5.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

Recorded evaluation configuration: {"Shot":"Few"}. This record does not assert independent reproduction.

### Llama 3.3 70B

Kendall Correlation: 0.73. Result ID: 69b12ae56dbb7075b95b9dd7.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

Recorded evaluation configuration: {"Shot":"Few"}. This record does not assert independent reproduction.

### Qwen 3 30B

Kendall Correlation: 0.709. Result ID: 69b12ae56dbb7075b95b9dd9.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

Recorded evaluation configuration: {"Shot":"Few"}. This record does not assert independent reproduction.

### Llama 4 Scout

Kendall Correlation: 0.704. Result ID: 69b12ae56dbb7075b95b9dd6.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

Recorded evaluation configuration: {"Shot":"Zero"}. This record does not assert independent reproduction.

### Llama 3.3 70B

Kendall Correlation: 0.656. Result ID: 69b12ae56dbb7075b95b9dd8.

[Reporting paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b0f7292d603e6de3e45f20.md>)

Recorded evaluation configuration: {"Shot":"Zero"}. This record does not assert independent reproduction.

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