PLSQLBench - MBPP+ (Test): leaderboard
Mean test pass at one on 308 MBPP+ problems translated to PL/SQL in PLSQLBench (2026), execution-based, in percent; higher is better.
Metric: Mean test pass@1 (%; the 308 MBPP+ problems translated to PL/SQL with withheld expanded unit tests; 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 July 2028. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Opus 4.8 | 47.73 | #56 |
| 2 | GPT-5.6 Sol | 46.75 | #29 |
| 3 | GPT-5.4 | 42.21 | #121 |
| 4 | Gemma 4 31B | 39.94 | #393 |
| 5 | GPT-5.4 Mini | 38.96 | #389 |
| 6 | Grok 4.3 | 38.31 | #332 |
| 7 | Gemini 2.5 Flash Lite | 33.44 | #958 |
| 8 | Llama 4 Maverick | 26.3 | #1105 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=plsqlbench-mbpp-plus-test · How It Works · Data refreshed daily, snapshot 2026-11-12.