Leaderboard Leaderboards / HELM
HELM
Holistic evaluation suites (Capabilities, Safety, Lite, MMLU and more). Full raw results sit in a public cloud bucket.
- Operator
- Stanford CRFM
- Leaderboard
- crfm.stanford.edu
- Category
- General / multi-benchmark
- How results are made
- Operator runs the evals
- Checked
- 2026-10-31
Raw data
| Format | Where |
|---|---|
| Public GCS bucket | crfm-helm.readthedocs.io/en/latest/downloading_raw_results/ gs://crfm-helm-public, public unauthenticated access. “All of HELM's raw result data is stored in Google Cloud Storage (GCS) in the public crfm-helm-public bucket.” (crfm-helm.readthedocs.io) |
Licence / reuse: Unclear
Apache-2.0 (licence of the repository that holds the result files). A licence exists, but it covers the code or website rather than clearly the results.
“Apache License Version 2.0, January 2004”
Source: raw.githubusercontent.com/stanford-crfm/helm/main/LICENSE
Apache-2.0 covers the HELM code repo. We found no separate licence statement for the bucket data.
Submissions: Not stated
We found no statement about outside submissions.
Last updated: 2026-06-05 148 days old
- 2026-06-05: Last commit to the GitHub repo · github.com
This page lists where the data lives and what the licence says. It does not copy any scores; open the leaderboard for those. Not legal advice. Something wrong? Use the bug link in the footer. Back to all leaderboards.