Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
String Extraction on ShellOps
Loading...
48.5
Exact Match
A³
17.3
25.4
33.5
41.6
May 8, 2026
Exact Match
Updated 23d ago
Evaluation Results
Method
Method
Links
Exact Match
A³
variant=σ-Reveal
2026.05
48.5
A³
variant=Vanilla
2026.05
46.5
LATS
2026.05
27.5
ReACT
2026.05
26
GSPO
2026.05
25.5
GiGPO
2026.05
24
HGPO
2026.05
23.5
RetroAgent
2026.05
19.5
rStar
2026.05
18.5
Feedback
Search any
task
Search any
task