Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prompt Optimization on PUPA
Loading...
91.85
Score
GEPA
80.3788
83.3569
86.335
89.3131
May 10, 2026
Score
Optimization Budget (# Rollouts)
Updated 22d ago
Evaluation Results
Method
Method
Links
Score
Optimization Budget (# Rollouts)
GEPA
Task Model=Qwen 3 8B
2026.05
91.85
2,426
LEVI
Task Model=Qwen 3 8B
2026.05
89.73
1,275
MIPROv2
Task Model=Qwen 3 8B
2026.05
81.55
-
Baseline
Task Model=Qwen 3 8B
2026.05
80.82
-
Feedback
Search any
task
Search any
task