Temporal Reasoning (date_season) on Synthetic Temporal Dataset (10-fold CV)
6.047Loss (Negative Log S)Llama-3.1-70B-IT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Llama-3.1-70B-ITManifold=clust2025.10 | 6.047 | 83 | |
| Llama-3.1-8B-ITManifold=clust2025.10 | 6.628 | 66 | |
| Llama-3.2-3BManifold=clust2025.10 | 6.78 | 53 | |
| Llama-3.2-3B-ITManifold=clust2025.10 | 7.031 | 74 | |
| gemma-2-2bManifold=clust2025.10 | 7.358 | 61 | |
| gemma-2-2b-ITManifold=clust2025.10 | 7.408 | 29 | |
| Qwen2.5-3BManifold=clust2025.10 | 8.439 | 55 | |
| Qwen2.5-3B-ITManifold=clust2025.10 | 8.502 | 26 |