PLSQLBench - Spider2 Multi-Turn (Test): leaderboard

Metric: Mean test pass@1 (%; the turns of the 63 held-out, database-disjoint multi-turn Spider 2 conversations, each turn conditioned on the model own earlier answers; direct generation of Oracle PL/SQL program units at temperature 0, executed on Oracle Autonomous Database 23ai; per-task fraction of unit tests passed by one solution, averaged over tasks). Source: arxiv.org. Saturation forecast: Around March 2028. 8 models tracked.

Top models

#ModelScore
1GPT-5.473.19
2Gemma 4 31B70.57
3GPT-5.6 Sol66.81
4Claude Opus 4.866.4
5GPT-5.4 Mini65.94
6Grok 4.365.46
7Gemini 2.5 Flash Lite56.78
8Llama 4 Maverick52.85

Interactive version: theaggregate.ai/benchmark?slug=plsqlbench-spider2-multi-turn-test · How It Works · Data refreshed daily, snapshot 2026-09-26.