Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Database Question Answering on EHRSQL (test)
Loading...
35
Execution Accuracy
GATE
26.056
28.378
30.7
33.022
Jun 4, 2026
Execution Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Execution Accuracy
GATE
Backbone=Qwen3-8B
2026.06
35
GATE
Backbone=GPT-5.4-mini
2026.06
34.4
ReAct
Backbone=GPT-5.4-mini
2026.06
32.2
ReFoRCE
Backbone=Qwen3-8B
2026.06
31.2
ReAct
Backbone=Qwen3-8B
2026.06
30.2
ReFoRCE
Backbone=GPT-5.4-mini
2026.06
27.6
ReDel
Backbone=GPT-5.4-mini
2026.06
26.8
ReDel
Backbone=Qwen3-8B
2026.06
26.4
Feedback
Search any
task
Search any
task