List your company
ResearchFormerly WizWand

Text-to-SQL Parsing on Ambrosia Unambiguous (test)

88.7RecallIntentRL
19.33237.34155.3573.359Nov 13, 2025
Updated 8mo ago

Evaluation results

MethodLinks
IntentRLModel=4B Instruct, Output Format=Interpretation-Answer Pairs2025.1188.774.7
SFTModel=4B Instruct, Output Format=Answer-only2025.117873.4
SFTModel=4B Instruct, Output Format=Interpretation-Answer Pairs2025.1177.774.7
IntentPromptModel=235B MoE Instruct, Output Format=Interpretation-Answer Pairs2025.1174.157.8
IntentPromptModel=235B MoE Instruct, Output Format=Answer-only2025.1169.364.1
IntentPromptModel=235B MoE Thinking, Output Format=Answer-only2025.1161.848.4
IntentPromptModel=4B Instruct, Output Format=Answer-only2025.1158.357.2
IntentPromptModel=4B Thinking, Output Format=Answer-only2025.1158.356.1
IntentPromptModel=235B MoE Thinking, Output Format=Interpretation-Answer Pairs2025.1153.735.9
IntentPromptModel=4B Thinking, Output Format=Interpretation-Answer Pairs2025.1125.219.7
IntentPromptModel=4B Instruct, Output Format=Interpretation-Answer Pairs2025.112218.8