Humor Evaluation on Grounded Satire Yle news
3.96Average ScoreLlama-3.1-8B-Instruct
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Llama-3.1-8B-InstructParameters=8B, Variant=Instruct2026.05 | 3.96 | 0.084 | |
| Aya-Expanse-8BParameters=8B2026.05 | 3.83 | 0.199 | |
| Qwen2.5-7B-InstructParameters=7B, Variant=Instruct2026.05 | 3.52 | 0.069 | |
| EuroLLM-9B-InstructParameters=9B, Variant=Instruct2026.05 | 3.46 | 0.161 | |
| Mistral-7B-Instruct-v0.3Parameters=7B, Variant=Instruct-v0.32026.05 | 2.81 | -0.065 |