Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prompt Optimization on 10-task prompt optimization suite GSM8K MMLU BBH
Loading...
81
Average Win/Tie Rate
ReElicit
38.36
49.43
60.5
71.57
May 18, 2026
Average Win/Tie Rate
Win/Tie Rate (vs ReElicit)
Win/Tie Rate (vs APE)
Win/Tie Rate (vs OPRO)
Win/Tie Rate (vs PromptBreeder)
Win/Tie Rate (vs TextGrad)
Updated 14d ago
Evaluation Results
Method
Method
Links
Average Win/Tie Rate
Win/Tie Rate (vs ReElicit)
Win/Tie Rate (vs APE)
Win/Tie Rate (vs OPRO)
Win/Tie Rate (vs PromptBreeder)
Win/Tie Rate (vs TextGrad)
ReElicit
Number of prompt evalu...
2026.05
81
-
78
79
85
82
OPRO
Number of prompt evalu...
2026.05
58
31
66
-
71
63
APE
Number of prompt evalu...
2026.05
56
30
-
60
71
63
TextGrad
Number of prompt evalu...
2026.05
49
26
48
51
70
-
PromptBreeder
Number of prompt evalu...
2026.05
40
22
44
45
-
48
Feedback
Search any
task
Search any
task