HarnessSQL Uses DeepSeek Harness to Lift an 8B Model to 45.2% on Spider 2.0-SQLite

HKUST's HarnessSQL trains small models inside DeepSeek Harness, lifting an 8B model from 15.5% to 45.2% on Spider 2.0-SQLite and past 32B baselines that score about 16%.

Sources

HarnessSQL Uses DeepSeek Harness to Lift an 8B Model to 45.2% on Spider 2.0-SQLite · TechNews