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

Question Answering on TQA

92.3Accuracy

RankRAG-70B

Updated 2d ago

Evaluation Results

Method	Links
RankRAG-70B 2026.03		92.3
RankRAG-8B 2026.03		89.5
Llama3.1-70B+Hit-RAG 2026.03		84.6
ETTC 2026.05		83.9
Llama3.1-70B+R-Ins 2026.03		83.8
Voting 2026.05		83.65
Qwen3-32B+Hit-RAG 2026.03		81.7
Llama3.1-8B+R-Ins 2026.03		80
Qwen3-8B+Hit-RAG 2026.03		78.9
Gemma-12B 2026.05		78.86
Qwen-7B 2026.05		78.5
Sonnet-3.5 2026.03		78.4
Pixtral-12B 2026.05		77.34
Qwen3-4B+Hit-RAG 2026.03		74.4
ChatGPT 2026.03		74.3
Speculative RAG-7B 2026.03		74.2
Llama3.1-8B+Hit-RAG 2026.03		74
LogicGaze 2026.01		73.8
RAS-8B 2026.03		73.8
RAS-7B 2026.03		72.7
IterDRAG 2026.01		71.9
RankRAG 2026.01		71.7
LogicGaze 2026.01		71.5
LLaMA-11B 2026.05		70.41
AutoRAG 2026.01		70.4
RankRAG 2026.01		70.2
IterDRAG 2026.01		69.9
Self-RAG-13B 2026.03		69.3
RQ-RAG 2026.01		68.6
AutoRAG 2026.01		68.5
Llama3.1-70B 2026.03		68.5
RQ-RAG 2026.01		67.4
Alpaca-13B 2026.03		66.9
Self-RAG 2026.01		66.5
Self-RAG-7B 2026.03		66.4
Qwen3-32B 2026.03		65.9
Ret-ChatGPT 2026.03		65.7
Self-RAG 2026.01		65.6
SFT+Ret 2026.01		61.3
Alpaca-13B 2026.03		61.3
GPT-4o-mini 2026.01		60.1
SFT 2026.01		59.2
Llama3.1-8B 2026.03		58.4
SAIL-7B 2026.01		57.5
SFT+Ret 2026.01		57.4
Qwen3-8B 2026.03		57.3
GPT-4o 2026.01		56.2
SFT 2026.01		55
SPAR-K 2026.03		51
Qwen3-4B 2026.03		50.1
SPAR-K 2026.03		49.2
Step-Audio-2 2026.03		49.1
SPAR-K 2026.03		48.7
Zero-Shot-Instruct+Ret 2026.01		48.3
Step-Audio-2 2026.03		46.7
Zero-Shot-Instruct 2026.01		46.3
Zero-Shot-Chat+Ret 2026.01		45.9
SAIL-7B 2026.01		45.9
GLM-4-Voice 2026.03		45.7
Zero-Shot-Chat 2026.01		45.5
GLM-4-Voice 2026.03		45
GLM-4-Voice 2026.03		44.9
SPAR-K 2026.03		44.7
SPAR-K 2026.03		43
Zero-Shot+Ret 2026.01		42.7
Zero-Shot+Ret 2026.01		42.6
SPAR-K 2026.03		42
SPAR-K 2026.03		41.8
SPAR-K 2026.03		41.2
Zero-Shot 2026.01		41
SPAR-K 2026.03		38.5
RoPE++EH 2025.12		37.1
RoPE++EC 2025.12		36.6
RoPE 2025.12		36.4
RoPE 2025.12		36.3
RoPE++EH 2025.12		36.1
RoPE++EC 2025.12		35.1
Zero-Shot 2026.01		30.2
Step-Audio-2 2026.03		28.5
SPAR-K 2026.03		0