Question Answering Evaluation on CUS-QA en
91.7CS MetricQwen 3 30B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Qwen 3 30BShot=Zero2026.03 | 91.7 | 77.6 | 75.4 | |
| Llama 4 ScoutShot=Few2026.03 | 85.9 | 82.9 | 73.1 | |
| Llama 3.3 70BShot=Few2026.03 | 80.8 | 78.8 | 75.1 | |
| Qwen 3 30BShot=Few2026.03 | 79.6 | 79.2 | 65.1 | |
| Llama 4 ScoutShot=Zero2026.03 | 79.3 | 77.4 | 66.9 | |
| Llama 3.3 70BShot=Zero2026.03 | 62.1 | 65.2 | 58.3 |