List your company

Temporal Reasoning (duration) on Synthetic Temporal Dataset (10-fold CV)

2.721Negative Log Sgemma-2-2b
2.694242.874873.05553.23613Oct 1, 2025

Evaluation results

MethodLinks
gemma-2-2bManifold=log_lin2025.102.72111
Qwen2.5-3B-ITManifold=log_lin2025.102.80532
Llama-3.2-3BManifold=log_lin2025.102.87921
Qwen2.5-3BManifold=log_lin2025.102.95917
Llama-3.1-8B-ITManifold=log_lin2025.102.999
Llama-3.2-3B-ITManifold=log_lin2025.103.12430
Llama-3.1-70B-ITManifold=log_lin2025.103.19462
gemma-2-2b-ITManifold=log_lin2025.103.3926