Narrative Understanding on HS
87.8First-Token AccuracyPhi-4-14B
Evaluation Results
| Method | Links | |
|---|---|---|
| Phi-4-14BStrategy=Prefilling2025.05 | 87.8 | |
| Ministral-8BStrategy=Prefilling2025.05 | 86.5 | |
| Phi-4-14BStrategy=Prompt Engineering2025.05 | 85.6 | |
| Ministral-8BStrategy=FTP2025.05 | 81.1 | |
| Mistral-Nemo-12BStrategy=Prefilling2025.05 | 76.4 | |
| Gemma-2-9BStrategy=Prefilling2025.05 | 69.8 | |
| Llama-3.1-8BStrategy=Prefilling2025.05 | 69 | |
| Ministral-8BStrategy=Prompt Engineering2025.05 | 68.6 | |
| Qwen-2-7BStrategy=Prefilling2025.05 | 65.2 | |
| Qwen-2-7BStrategy=Prompt Engineering2025.05 | 65 | |
| Gemma-2-9BStrategy=Prompt Engineering2025.05 | 63.6 | |
| Phi-4-14BStrategy=FTP2025.05 | 61.2 | |
| Gemma-7BStrategy=Prefilling2025.05 | 56.3 | |
| Qwen-2-7BStrategy=FTP2025.05 | 53.4 | |
| Mistral-Nemo-12BStrategy=Prompt Engineering2025.05 | 52.6 | |
| Llama-3.1-8BStrategy=FTP2025.05 | 52.2 | |
| Mistral-Nemo-12BStrategy=FTP2025.05 | 51.6 | |
| Llama-3.1-8BStrategy=Prompt Engineering2025.05 | 49.2 | |
| Gemma-7BStrategy=Prompt Engineering2025.05 | 43.9 | |
| Gemma-2-9BStrategy=FTP2025.05 | 43 | |
| Zephyr-7BStrategy=Prompt Engineering2025.05 | 40 | |
| Gemma-7BStrategy=FTP2025.05 | 36.3 | |
| Zephyr-7BStrategy=Prefilling2025.05 | 36.1 | |
| Zephyr-7BStrategy=FTP2025.05 | 35 |