Narrative Understanding on SC
98.7First-Token AccuracyPhi-4-14B
Evaluation Results
| Method | Links | |
|---|---|---|
| Phi-4-14BStrategy=Prompt Engineering2025.05 | 98.7 | |
| Phi-4-14BStrategy=Prefilling2025.05 | 98.7 | |
| Ministral-8BStrategy=Prefilling2025.05 | 98.2 | |
| Phi-4-14BStrategy=FTP2025.05 | 98.2 | |
| Gemma-2-9BStrategy=Prompt Engineering2025.05 | 97.9 | |
| Gemma-2-9BStrategy=Prefilling2025.05 | 97.9 | |
| Qwen-2-7BStrategy=Prompt Engineering2025.05 | 97.7 | |
| Gemma-2-9BStrategy=FTP2025.05 | 97.6 | |
| Ministral-8BStrategy=FTP2025.05 | 97.4 | |
| Qwen-2-7BStrategy=Prefilling2025.05 | 97.3 | |
| Mistral-Nemo-12BStrategy=FTP2025.05 | 97.3 | |
| Qwen-2-7BStrategy=FTP2025.05 | 97.1 | |
| Mistral-Nemo-12BStrategy=Prefilling2025.05 | 96.9 | |
| Llama-3.1-8BStrategy=Prefilling2025.05 | 96.4 | |
| Zephyr-7BStrategy=FTP2025.05 | 96 | |
| Zephyr-7BStrategy=Prefilling2025.05 | 96 | |
| Llama-3.1-8BStrategy=Prompt Engineering2025.05 | 94.8 | |
| Ministral-8BStrategy=Prompt Engineering2025.05 | 94 | |
| Llama-3.1-8BStrategy=FTP2025.05 | 93.2 | |
| Gemma-7BStrategy=Prefilling2025.05 | 92 | |
| Zephyr-7BStrategy=Prompt Engineering2025.05 | 91.7 | |
| Mistral-Nemo-12BStrategy=Prompt Engineering2025.05 | 89.9 | |
| Gemma-7BStrategy=Prompt Engineering2025.05 | 77.2 | |
| Gemma-7BStrategy=FTP2025.05 | 69.6 |