Narrative Understanding on MC-T
93.3First-Token AccuracyZephyr-7B
Evaluation Results
| Method | Links | |
|---|---|---|
| Zephyr-7BStrategy=Prefilling2025.05 | 93.3 | |
| Mistral-Nemo-12BStrategy=Prefilling2025.05 | 93.3 | |
| Mistral-Nemo-12BStrategy=Prompt Engineering2025.05 | 92.8 | |
| Mistral-Nemo-12BStrategy=FTP2025.05 | 92.4 | |
| Ministral-8BStrategy=Prefilling2025.05 | 91.9 | |
| Ministral-8BStrategy=FTP2025.05 | 91.5 | |
| Gemma-7BStrategy=Prompt Engineering2025.05 | 91 | |
| Gemma-7BStrategy=Prefilling2025.05 | 91 | |
| Ministral-8BStrategy=Prompt Engineering2025.05 | 90 | |
| Llama-3.1-8BStrategy=Prompt Engineering2025.05 | 89.7 | |
| Qwen-2-7BStrategy=FTP2025.05 | 88.3 | |
| Qwen-2-7BStrategy=Prefilling2025.05 | 86.1 | |
| Phi-4-14BStrategy=Prefilling2025.05 | 86.1 | |
| Zephyr-7BStrategy=Prompt Engineering2025.05 | 85.2 | |
| Qwen-2-7BStrategy=Prompt Engineering2025.05 | 85.1 | |
| Llama-3.1-8BStrategy=Prefilling2025.05 | 82.5 | |
| Phi-4-14BStrategy=FTP2025.05 | 82.5 | |
| Llama-3.1-8BStrategy=FTP2025.05 | 82.1 | |
| Phi-4-14BStrategy=Prompt Engineering2025.05 | 82 | |
| Gemma-2-9BStrategy=Prefilling2025.05 | 78.5 | |
| Gemma-2-9BStrategy=Prompt Engineering2025.05 | 77.1 | |
| Gemma-2-9BStrategy=FTP2025.05 | 72.2 | |
| Zephyr-7BStrategy=FTP2025.05 | 69.1 | |
| Gemma-7BStrategy=FTP2025.05 | 60.1 |