Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool Selection on EnterpriseArena
Loading...
45
Tool Selection Accuracy
Gemini-2.5 Pro
8.6
18.05
27.5
36.95
Mar 23, 2026
Tool Selection Accuracy
Updated 25d ago
Evaluation Results
Method
Method
Links
Tool Selection Accuracy
Gemini-2.5 Pro
Model Category=Closed-...
2026.03
45
Claude-3.5-Sonnet
Model Category=Closed-...
2026.03
43
GPT-4o
Model Category=Closed-...
2026.03
31
Qwen3-8B Agentic GRPO
Model Category=Our Pla...
2026.03
28
Qwen3-8B SFT
Model Category=Our Pla...
2026.03
20
ToolAce
Model Category=Open-So...
2026.03
15
Qwen3-8B Base
Model Category=Open-So...
2026.03
14
xLAM-2-70B
Model Category=Open-So...
2026.03
10
Feedback
Search any
task
Search any
task