Political Relevance Evaluation on Grounded Satire Yle news
3.5Average ScoreQwen2.5-7B-Instruct
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-7B-InstructParameters=7B, Variant=Instruct2026.05 | 3.5 | 0.688 | |
| Aya-Expanse-8BParameters=8B2026.05 | 3.4 | 0.826 | |
| Llama-3.1-8B-InstructParameters=8B, Variant=Instruct2026.05 | 3.21 | 0.756 | |
| EuroLLM-9B-InstructParameters=9B, Variant=Instruct2026.05 | 2.41 | 0.663 | |
| Mistral-7B-Instruct-v0.3Parameters=7B, Variant=Instruct-v0.32026.05 | 1.83 | 0.751 |