Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on Wiki-based QA Finance (overall)
Loading...
3.9
LLM-as-judge Score (1-5)
No Wiki (direct LLM)
3.6608
3.7229
3.785
3.8471
Jun 3, 2026
LLM-as-judge Score (1-5)
Updated 1mo ago
Evaluation Results
Method
Method
Links
LLM-as-judge Score (1-5)
No Wiki (direct LLM)
N=200
2026.06
3.9
Static Wiki (baseline)
N=200
2026.06
3.83
Online WiCER
N=173
2026.06
3.79
FIFO (recency only)
N=173
2026.06
3.7
Oracle (GT labels)
N=173
2026.06
3.67
Feedback
Search any
task
Search any
task