CodeScope - Code Summarization — leaderboard
Metric: Score. Source: haitianliu22.github.io. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 | 33.66 |
| 2 | GPT-3.5 | 33.18 |
| 3 | starcoder | 31.16 |
Interactive version: aibenchmarks.dev/benchmark?slug=codescope-code-summarization · How the rankings work · Data refreshed daily, snapshot 2026-07-08.