NLG Meta-evaluation on CUS-QA en (sk)
0.661Kendall CorrelationLlama 4 Scout
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama 4 ScoutShot=Few2026.03 | 0.661 | |
| Llama 4 ScoutShot=Zero2026.03 | 0.624 | |
| Qwen 3 30BShot=Few2026.03 | 0.619 | |
| Llama 3.3 70BShot=Few2026.03 | 0.598 | |
| Llama 3.3 70BShot=Zero2026.03 | 0.519 | |
| Qwen 3 30BShot=Zero2026.03 | 0.513 |