Question Answering on IndiRef Meetup
50Temporal Score (FEM)Gemma2 - 27B
Evaluation results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Gemma2 - 27BContext=Full Dialog History2026.01 | 50 | 44 | 58 | 56 | 48 | 44 | 28 | 26 | |
| Gemma2 - 9BContext=Full Dialog History2026.01 | 48 | 38 | 50 | 46 | 38 | 40 | 26 | 18 | |
| Llama3.1 - 8BContext=Full Dialog History2026.01 | 38 | 32 | 46 | 38 | 46 | 44 | 20 | 20 | |
| Qwen QwQ - 32BContext=Full Dialog History2026.01 | 38 | 32 | 52 | 38 | 44 | 40 | 40 | 40 | |
| Gemma2 - 2BContext=Full Dialog History2026.01 | 20 | 18 | 18 | 16 | 24 | 26 | 26 | 16 |