Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool-use Generalization on ACEBench Content OOD v1 (test)
Loading...
40
Adherence
Vanilla
-1.6
9.2
20
30.8
Jun 24, 2026
Adherence
Success Rate
Success Failure Score
Average Multi Turn Score
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Adherence
Success Rate
Success Failure Score
Average Multi Turn Score
Average Score
Vanilla
Backbone=Qwen2.5-1.5B-...
2026.06
40
32
52
2.5
31.6
SFT_BFCL
Backbone=Qwen2.5-1.5B-...
2026.06
30
20
44
2.5
24.1
ETS
Backbone=Qwen2.5-1.5B-...
2026.06
26
22
36
2.5
21.6
PRS
Backbone=Qwen2.5-1.5B-...
2026.06
26
30
43
4.2
25.8
OPS
Backbone=Qwen2.5-1.5B-...
2026.06
20
16
50
6.7
23.2
SFT_BFCL + RL
Backbone=Qwen2.5-1.5B-...
2026.06
8
8
10
0
6.5
GRPO
Backbone=Qwen2.5-1.5B-...
2026.06
0
0
0
0
0
HBG
Backbone=Qwen2.5-1.5B-...
2026.06
0
0
0
0
0
Feedback
Search any
task
Search any
task