List your company

Text-to-SQL on BiomedSQL (test)

90Execution Accuracy (EX)Domain Expert
22.9240.33557.7575.165May 23, 2025

Evaluation results

MethodLinks
Domain Expert2025.05909095——
BMSQL-GPT-o3-miniparadigm=BMSQL, backbone=GPT-o3-mini, # Tokens=39,4702025.0562.669.283.1382.6
DAIL-SQL-GPT-o3-miniparadigm=DAIL-SQL, backbone=GPT-o3-mini, # Tokens=3,3182025.0561.263.681.442.10
BMSQL-GPT-4oparadigm=BMSQL, backbone=GPT-4o, # Tokens=32,8192025.0560.467.279.864.54.9
Claude-4.5-Opus# Tokens=4,1972025.0558.459.780.635.80
Gemini-3-Pro# Tokens=3,1362025.0558.162.481.852.40
ReAct-GPT-o3-miniparadigm=ReAct, backbone=GPT-o3-mini, # Tokens=13,3172025.0556.264.873.613.20
BMSQL-Gemini*paradigm=BMSQL, backbone=Gemini-2.0-Flash, # Tokens=22,0452025.0555.961.384.632.10.2
DAIL-SQL-GPT-4oparadigm=DAIL-SQL, backbone=GPT-4o, # Tokens=3,6242025.0554.858.175.563.46.6
GPT-o3-mini# Tokens=3,9422025.0553.560.473.329.40.2
DAIL-SQL-Gemini*paradigm=DAIL-SQL, backbone=Gemini-2.0-Flash, # Tokens=3,1852025.0553.158.882.830.60
ReAct-GPT-4oparadigm=ReAct, backbone=GPT-4o, # Tokens=14,2862025.0549.657.967.28.90
ReAct-Gemini*paradigm=ReAct, backbone=Gemini-2.0-Flash, # Tokens=13,2052025.0548.956.660.410.20
GPT-5.2# Tokens=4,5982025.0548.554.675.335.62.7
GPT-4o# Tokens=3,6892025.0546.954.771.226.11.3
Index-Gemini*paradigm=Index, backbone=Gemini-2.0-Flash, # Tokens=7872025.0546.148.554.259.68.1
Claude-3.7-Sonnet# Tokens=3,8052025.0545.449.869.8431.6
Qwen-2.5-Coder-32B# Tokens=3,6122025.0540.844.458.26115.7
Llama-3.1-405B# Tokens=3,4562025.0538.142.557.941.74.6
Qwen-2.5-Coder-14B# Tokens=3,4532025.053732.462.142.511
Llama-3.1-70B# Tokens=3,5472025.0534.439.857376
Gemini-2.0-Flash# Tokens=3,6922025.0533.73771.127.24.2
Index-GPT-o3-miniparadigm=Index, backbone=GPT-o3-mini, # Tokens=1,8992025.0527.130.644.147.52
Index-GPT-4oparadigm=Index, backbone=GPT-4o, # Tokens=1,1102025.0525.528.344.166.927.5