Code Generation Eval
Sample dataCode generation
Definition & methodology
- Methodology
- Sample methodology: models generate solutions to programming tasks, graded by unit tests.
- Dataset
- Sample dataset of function-level programming problems with hidden test suites.
- Metric
- pass@1 (%) (higher is better)
- Version
- 1.2
- Last updated
- 2026-08-01
- Limitations
- Sample limitation note: limited language coverage in this demo dataset.
Model results
| Model | Score | Sample size | Evidence | Evaluated |
|---|---|---|---|---|
| GPT Frontier | 80 % | 300 | L2Benchmark Result | 2026-08-01 |
| Claude Sonnet | 78 % | 300 | L2Benchmark Result | 2026-08-01 |
| Gemini Pro | 75 % | 300 | L2Benchmark Result | 2026-08-01 |