Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-step reasoning on Bamboogle (test)
Loading...
75.2
Accuracy
CAHL
66.88
69.04
71.2
73.36
Dec 15, 2023
May 14, 2024
Oct 12, 2024
Mar 12, 2025
Aug 10, 2025
Jan 8, 2026
Jun 8, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
CAHL
2026.06
75.2
ReST meets ReAct
Generation=2nd gen, Ba...
2023.12
74.4
TUMIX
2026.06
73.6
ToolRL
2026.06
72
Qwen
Base Model=Qwen-2.5-In...
2026.06
69.6
PaLM 2-L
Mode=Pre-trained, Back...
2023.12
68.8
EASYTool
2026.06
68.8
ReST meets ReAct
Generation=2nd gen, Ba...
2023.12
68
ReST meets ReAct
Generation=2nd gen, Ba...
2023.12
67.2
Feedback
Search any
task
Search any
task