We select a representative set of Large Reasoning Models for evaluation, covering both open-weights distilled models and advanced models. Specifically, we include:
Open-Weights Distilled Models: We evaluate the DeepSeek-R1-Distill family to analyze the impact of model scale and base architecture. This includes the Qwen-based variants (7B, 14B, 32B) and the Llama-based variant (Llama-8B). All distilled models are deployed locally.
Advanced Models: We evaluate DeepSeek-R1 and GPT-5-mini (with reasoning features enabled) via their respective APIs. These models serve as the topline performance baseline.
All models are configured with a maximum generation length of 8,192 tokens to accommodate the potentially extended reasoning traces required for complex temporal deduction.