HELM Classic - APPS (Code): leaderboard
The "APPS (Code)" subtask of HELM Classic. A scenario from Stanford HELM Classic, the holistic evaluation suite scoring language models across accuracy, robustness and calibration on a broad set of tasks.
Metric: Average Tests Passed (%). Source: crfm.stanford.edu. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | code-davinci-002 | 20.04 | |
| 2 | code-cushman-001 (12B) | 4.82 |
Interactive version: theaggregate.ai/benchmark?slug=helm-classic-apps-code · How It Works · Data refreshed daily, snapshot 2026-10-20.