Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Systems Optimization on LLM-SQL
Loading...
0.731
Final Score
CORAL
0.69044
0.70097
0.7115
0.72203
Apr 2, 2026
Apr 6, 2026
Apr 10, 2026
Apr 14, 2026
Apr 18, 2026
Apr 22, 2026
Apr 27, 2026
Final Score
Improvement Rate
# Evaluations
Updated 1mo ago
Evaluation Results
Method
Method
Links
Final Score
Improvement Rate
# Evaluations
CORAL
Agent Model=Claude Cod...
2026.04
0.731
53.3
15
SOTA
2026.04
0.73
-
-
EvoX
Agent Model=Claude Cod...
2026.04
0.726
6
83
ShinkaEvolve
Agent Model=Claude Cod...
2026.04
0.724
23.8
21
SEAEVOSHINKA
Backbone=Gemini-3-Flash
2026.04
0.72
-
-
OpenEvolve
Agent Model=Claude Cod...
2026.04
0.716
6.7
100
GEPA
Backbone=Gemini-3-Flash
2026.04
0.7158
-
-
OpenEvolve
Backbone=Gemini-3-Flash
2026.04
0.7117
-
-
SEAEVOOPEN
Backbone=Gemini-3-Flash
2026.04
0.7104
-
-
ShinkaEvolve
Backbone=Gemini-3-Flash
2026.04
0.6998
-
-
Human/SOTA
2026.04
0.692
-
-
Feedback
Search any
task
Search any
task