List your company

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

1.14Log LossQwen2.5-3B-IT
1.125321.224411.32351.42259Oct 1, 2025

Evaluation results

MethodLinks
Qwen2.5-3B-ITManifold=circ2025.101.1419
gemma-2-2b-ITManifold=semic2025.101.2567
Llama-3.2-3B-ITManifold=circ2025.101.27830
Llama-3.2-3BManifold=circ2025.101.28410
Qwen2.5-3BManifold=circ2025.101.28724
Llama-3.1-8B-ITManifold=circ2025.101.29812
Llama-3.1-70B-ITManifold=circ2025.101.48253
gemma-2-2bManifold=circ2025.101.50718