Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-document Question Answering on FinanceBench (FB)
Loading...
89.33
Accuracy
SLIDERS
61.6036
68.8018
76
83.1982
Apr 24, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
SLIDERS
LLMs=GPT 4.1 & GPT 4.1...
2026.04
89.33
Basemodel
LLMs=Qwen3.5 122B-A10B
2026.04
84.67
SLIDERS
LLMs=Qwen3.5 122B-A10B
2026.04
82.1
Basemodel
LLMs=GPT 4.1
2026.04
82
GraphRAG
LLMs=Qwen3-4B & GPT 4.1
2026.04
75.33
RLM
LLMs=GPT 5 & GPT 5-mini
2026.04
75.33
LongRAG
LLMs=Qwen3-4B & GPT 4.1
2026.04
72
Chain of Agent
LLMs=GPT 5 & GPT 5-mini
2026.04
71.3
DocETL
LLMs=GPT 4.1
2026.04
63.33
RAG
LLMs=Qwen3-4B & GPT 4.1
2026.04
62.67
Feedback
Search any
task
Search any
task