List your company

Temporal Question Answering on TimeQA Hard v1

0.504R-1CoT+RL pipeline
0.123360.222180.3210.41982Feb 4, 2026

Evaluation results

MethodLinks
CoT+RL pipelinePrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-1.5B, Training Method=RL2026.020.5040.3950.5040.68135.75
CoT+RL pipelinePrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-0.5B, Training Method=RL2026.020.4110.310.410.62625.26
SFTPrompt Type=W/ TIME SUB-C, Model=Qwen2.5-7B2026.020.3740.2320.3730.5521.96
SFTPrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-7B2026.020.370.180.3650.540.37
SFTPrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-1.5B2026.020.3150.1780.3140.5183.95
SFTPrompt Type=W/ TIME SUB-C, Model=Qwen2.5-1.5B2026.020.3110.1840.3110.5241.41
SFTPrompt Type=W/ KGS (WHOLE C) (FAISS), Model=Qwen2.5-7B2026.020.310.1740.3070.5070.26
SFTPrompt Type=W/ KGS (CHUNKED C) (FAISS), Model=Qwen2.5-7B2026.020.2710.1640.2690.4840.32
SFTPrompt Type=W/ KGS (WHOLE C) (FAISS), Model=Qwen2.5-1.5B2026.020.2670.180.2670.4620.39
LoRA (r=32)Prompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-1.5B2026.020.2460.1530.2430.4672.37
SFTPrompt Type=W/ KGS (CHUNKED C) (FAISS), Model=Qwen2.5-1.5B2026.020.2250.120.2250.470.13
ClassifierPrompt Type=W/ ORIGINAL CONTEXT (C), Model=Qwen2.5-7B2026.020.1380.1280.1370.35712.4