Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Text-to-SQL on Ambrosia
Loading...
64.18
AUPRC
HEROSQL
57.628
59.329
61.03
62.731
Dec 28, 2025
AUPRC
AUROC
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUPRC
AUROC
HEROSQL
Backbone=Qwen3-0.6b
2025.12
64.18
57.28
TED
Backbone=Qwen3-0.6b
2025.12
63.91
56.95
HEROSQL
Backbone=Gemma-3-0.3b
2025.12
61.72
52.06
TED
Backbone=Gemma-3-0.3b
2025.12
60.51
50.7
ConfScore
Backbone=Qwen3-0.6b
2025.12
59.61
50.63
ConfScore
Backbone=Gemma-3-0.3b
2025.12
59.58
51.56
CoT
Backbone=Qwen3-0.6b
2025.12
59.04
49.79
COVE
Backbone=Gemma-3-0.3b
2025.12
58.64
50.58
CoT
Backbone=Gemma-3-0.3b
2025.12
58.38
50.04
prompt
Backbone=Gemma-3-0.3b
2025.12
58.36
50
prompt
Backbone=Qwen3-0.6b
2025.12
58.18
48.75
COVE
Backbone=Qwen3-0.6b
2025.12
57.88
48.8
Feedback
Search any
task
Search any
task
