NLG Meta-evaluation on CUS-QA en uk
0.577Kendall CorrelationQwen 3 30B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen 3 30BShot=Zero2026.03 | 0.577 | |
| Llama 3.3 70BShot=Few2026.03 | 0.524 | |
| Llama 4 ScoutShot=Few2026.03 | 0.492 | |
| Llama 4 ScoutShot=Zero2026.03 | 0.45 | |
| Qwen 3 30BShot=Few2026.03 | 0.429 | |
| Llama 3.3 70BShot=Zero2026.03 | 0.355 |