| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| BEAVER Oracle dialect | SOMA-SQL | Execution Accuracy36.4 | 9 | 1mo ago | |
| Archer Chinese zh (dev) | SOMA-SQL | Execution Accuracy (EX)84.6 | 9 | 1mo ago | |
| Spider 600 Q (test dev) | Gemini 2.5 F-Lite | Execution Accuracy73.83 | 7 | 4mo ago | |
| BIRD | Custom Orchestrator (V5) | California Schools Accuracy78.7 | 6 | 2mo ago | |
| Spider2-snow leaderboard (full) | QUVI-3 | Accuracy94.15 | 5 | 24d ago | |
| AMBROSIA Unambiguous | SOMA-SQL | Execution Accuracy (EX)94.7 | 3 | 1mo ago | |
| AMBROSIA Ambiguous | SOMA-SQL | Execution Accuracy (EX)92 | 3 | 1mo ago |