Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Cross-platform Tool Use on XBench
Loading...
37
Score
ZeroRL + ACTGUIDE-RL
16.2
21.6
27
32.4
May 12, 2026
Score
Updated 21d ago
Evaluation Results
Method
Method
Links
Score
ZeroRL + ACTGUIDE-RL
2026.05
37
SFT
2026.05
25
SFT + ACTGUIDE-RL
2026.05
25
ZeroRL
2026.05
18
SFT + RL
2026.05
17
Feedback
Search any
task
Search any
task