Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-document Question Answering on Loong
Loading...
78.57
Accuracy
SLIDERS
53.3812
59.9206
66.46
72.9994
Apr 24, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
SLIDERS
LLMs=GPT 4.1 & GPT 4.1...
2026.04
78.57
Basemodel
LLMs=GPT 4.1
2026.04
76.74
SLIDERS
LLMs=Qwen3.5 122B-A10B
2026.04
75.7
DocETL
LLMs=GPT 4.1
2026.04
75.03
Basemodel
LLMs=Qwen3.5 122B-A10B
2026.04
74.78
RLM
LLMs=GPT 5 & GPT 5-mini
2026.04
72.64
GraphRAG
LLMs=Qwen3-4B & GPT 4.1
2026.04
61.28
LongRAG
LLMs=Qwen3-4B & GPT 4.1
2026.04
59.1
Chain of Agent
LLMs=GPT 5 & GPT 5-mini
2026.04
54.46
RAG
LLMs=Qwen3-4B & GPT 4.1
2026.04
54.35
Feedback
Search any
task
Search any
task
