Share your thoughts, 1 month free Claude Pro on usSee more

Temporal Question Answering on TempReason OBQA-L3

49.8Exact Match (EM)

DeepSeek-V3-AdapTime

Updated 1mo ago

Evaluation Results

Method	Links
DeepSeek-V3-AdapTime 2026.04		49.8	53.2
DeepSeek-V3-Step-back 2026.04		48.8	52.3
DeepSeek-V3-CoT 2026.04		47	50.4
DeepSeek-V3-ICL 2026.04		43.6	48.3
GPT-4 2026.04		43.1	48.5
DeepSeek-V3-Self-refinement 2026.04		41.1	42.3
TG-LLM 2026.04		35.6	46.9
REMEMO-large 2026.04		33.4	49.3
T5-large 2026.04		28.8	46.8
Qwen-3-8B-CoT 2026.04		28.8	33.4
Qwen-3-8B-AdapTime 2026.04		28.8	33.8
REMEMO-base 2026.04		28.5	44.9
T5-base 2026.04		23.8	41.8
Qwen-3-8B-ICL 2026.04		23.1	32.7
LLaMA-3-8B-CoT 2026.04		16.5	24.1
LLaMA-3-8B-AdapTime 2026.04		14.5	22.5
LLaMA-3-8B-ICL 2026.04		1.8	10.5