Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Tool-use alignment on FA-Bench 500 queries
Loading...
91
TCR
ToolRLA
60.84
68.67
76.5
84.33
Mar 2, 2026
TCR
TIER
AIR
CRR
VR
Updated 3mo ago
Evaluation Results
Method
Method
Links
TCR
TIER
AIR
CRR
VR
ToolRLA
Latency=1.6s
2026.03
91
14
2.8
96
0.8
ReAct + GRPO (coarse)
Latency=1.9s
2026.03
82
21
3.1
74
6.5
ReAct + GRPO (additive)
Latency=1.8s
2026.03
80
22
3
75
6.2
ReAct + PPO (binary)
Latency=2.1s
2026.03
76
26
3.4
70
8
ReAct + SFT only
Latency=2.4s
2026.03
68
38
3.9
65
10.5
Multi-Model Pipeline
Latency=2.8s
2026.03
62
38
4.2
61
12
Feedback
Search any
task
Search any
task