Creative Writing (Poem) on FAITHQA (Omission)
60Perfect ScoreClaude-3.5
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Claude-3.52025.06 | 60 | 9.02 | |
| LLAMA3-70B2025.06 | 51 | 8.64 | |
| Claude-32025.06 | 47 | 8.45 | |
| GPT-4o2025.06 | 40 | 8.29 | |
| GPT-4o-mini2025.06 | 30 | 7.79 | |
| LLAMA3-8B2025.06 | 27 | 7.71 | |
| Mistral-7B2025.06 | 7 | 5.49 |