List your company

Temporal Question Answering on TimeQA Easy v1

58R-1 ScoreCoT+RL pipeline
14.21625.58336.9548.317Feb 4, 2026

Evaluation results

MethodLinks
CoT+RL pipelinePrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-1.5B, Training Method=RL2026.025845.657.872.243.41
SFTPrompt Type=W/ TIME SUB-C, Model=Qwen2.5-7B2026.0248.431.448.360.91.01
CoT+RL pipelinePrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-0.5B, Training Method=RL2026.0246.935.546.86632.48
SFTPrompt Type=W/ TIME SUB-C, Model=Qwen2.5-1.5B2026.0244.228.34458.71.08
SFTPrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-7B2026.0239.619.639.656.43.7
SFTPrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-1.5B2026.0235.918.335.754.31.81
SFTPrompt Type=W/ KGS (WHOLE C) (FAISS), Model=Qwen2.5-7B2026.0232.219.83251.11.4
LoRA (r=32)Prompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-1.5B2026.0232.118.431.651.91.29
SFTPrompt Type=W/ KGS (WHOLE C) (FAISS), Model=Qwen2.5-1.5B2026.0228.515.928.4490.07
SFTPrompt Type=W/ KGS (CHUNKED C) (FAISS), Model=Qwen2.5-7B2026.0227.115.42749.60.43
SFTPrompt Type=W/ KGS (CHUNKED C) (FAISS), Model=Qwen2.5-1.5B2026.0223.815.123.646.32.5
ClassifierPrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-7B2026.0215.912.615.838.711.41