Project AURIONAI Use-Cases Research & Innovation

HellaSwag

Commonsense completion (Gemma 3n PT card)

knowledge and reasoning
4scores
4models
0independent
0maintainer-run
4vendor-reported

Definition

Version
not in the notes
Category
knowledge and reasoning
Maintainer
not in the notes
Status
not in the notes
Home page
not in the notes

Sources

  1. Gemma 3n model card  |  Google AI for Developers ai.google.dev https://ai.google.dev/gemma/docs/gemma-3n/model_card

Scores at a Glance

Where this comes from
Each bar is one model, with its most independent recorded score. Hatched bars are vendor-reported; the word beside each bar says who ran it. Settings and dates differ between rows; the Scores table below has every result.

Scores

4 of 4 scores shown hellaswag-scores.csv
ModelScoreWho ran itSettingView or populationDateSource
DatabricksDBRX89 %vendor-reportedDBRX Instruct; 10-shot–27 Mar 2024databricks.com
CohereCommand R+ (Apr '24)88.6 %vendor-reportedOpen LLM Leaderboard figures as quoted on the model card–Apr 2024huggingface.co
Google DeepMindGemma 3n E4B78.6 %vendor-reportedPT (pretrained checkpoint)––ai.google.dev
Google DeepMindGemma 3n E2B72.2 %vendor-reportedPT (pretrained checkpoint)––ai.google.dev
Where this comes from
Scores from different settings, harnesses or dates are not directly comparable; the row says which. Sorted by score, highest first, as a reading aid, not a ranking.

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "HellaSwag", https://aurion.semai.id/benchmarks/hellaswag/, records of October 2026.