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

Open-domain Question Answering on TriviaQA (TQA)

0.4177Accuracy

UR-RAG

Updated 1mo ago

Evaluation Results

Method	Links
UR-RAG 2026.01		0.4177	0.4203
RePlug 2026.01		0.401	0.4077
LURE-RAG (w/o topics) 2026.01		0.401	0.4017
LURE-RAG 2026.01		0.3994	0.4039
Gemma3 1B 2026.03		0.398	-
k-shot 2026.01		0.3966	0.3954
UR-RAG 2026.01		0.3699	0.3497
LURE-RAG 2026.01		0.3635	0.3304
LURE-RAG (w/o topics) 2026.01		0.3628	0.322
MobileLLM-Flash 1.4B 2026.03		0.3606	-
RePlug 2026.01		0.3582	0.34
0-shot 2026.01		0.3566	0.3587
k-shot 2026.01		0.3509	0.3137
LFM2 1.2B 2026.03		0.335	-
UR-RAG 2026.01		0.3184	0.3098
RePlug 2026.01		0.3111	0.3042
LURE-RAG 2026.01		0.3059	0.2951
LURE-RAG (w/o topics) 2026.01		0.2994	0.2897
k-shot 2026.01		0.2834	0.262
0-shot 2026.01		0.2779	0.2214
MobileLLM-Flash 650M 2026.03		0.2449	-
Llama3.2 1B 2026.03		0.2381	-
0-shot 2026.01		0.2258	0.2137
LFM2 700M 2026.03		0.225	-
MobileLLM-Flash 350M 2026.03		0.1984	-
Gemma3 270M 2026.03		0.154	-
LFM2 350M 2026.03		0.1497	-
Qwen3 0.6B 2026.03		0.0241	-