HELM Classic - HumanEval (Code) — leaderboard
Metric: Pass@1 (%). Source: crfm.stanford.edu. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | code-davinci-002 | 46.34 |
| 2 | code-cushman-001 (12B) | 31.71 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-humaneval-code · How the rankings work · Data refreshed daily, snapshot 2026-07-22.