CodeScope - Program Synthesis — leaderboard
Metric: Score. Source: haitianliu22.github.io. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 | 36.36 |
| 2 | GPT-3.5 | 22.91 |
| 3 | starcoder | 0.5 |
Interactive version: theaggregate.ai/benchmark?slug=codescope-program-synthesis · How the rankings work · Data refreshed daily, snapshot 2026-07-22.