LiveCodeBench v5
LiveCodeBench version 5 (Gemma 3n card)
v5coding
Definition
- Version
- v5
- Category
- coding
- Maintainer
- UC Berkeley/MIT/Cornell authors, USA
- Status
- not in the notes
- Home page
- https://arxiv.org/abs/2403.07974
Sources
- 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
Score in %
Higher is better for this unit.
1
Gemma 3n E4BGoogle DeepMindITGemma 3n E2BGoogle DeepMindIT
Gemma 3n E4BGoogle DeepMindIT25.7 %
vendor-reported2Gemma 3n E2BGoogle DeepMindIT18.6 %
vendor-reported0255075100
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
| Model | Score | Who ran it | Setting | View or population | Date | Source |
|---|---|---|---|---|---|---|
| Gemma 3n E4B | 25.7 % | vendor-reported | IT | – | – | ai.google.dev |
| Gemma 3n E2B | 18.6 % | vendor-reported | IT | – | – | 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, "LiveCodeBench v5", https://aurion.semai.id/benchmarks/livecodebench-v5/, records of October 2026.