Identity
- Type
- company
- Country label
- USA
- HQ country
- USA
- Founding country
- not in the notes
- Parent
- not in the notes
- Parent country
- not in the notes
- Country basis
- the organisation's own page
Where this comes from
Convention D1: a dual label, HQ first, when the HQ, founding or parent country differ.
Models by Class
LLM1
Models
ModelClassOpennessParametersReleased
DBRXLLM27 Mar 2024Links
Organisation
Databrickscompany, USA
Databrickscompany, USAModels
DBRXDatabricks, LLM
DBRXDatabricks, LLMUse Casesnone recorded
Who Runs Itnone recorded
Models 1
Scores
| Benchmark | Model | Score | Who ran it | Setting |
|---|---|---|---|---|
| ARC-c | DBRX | 68.9 % | vendor-reported | DBRX Instruct; 25-shot |
| GSM8K | DBRX | 66.9 % | vendor-reported | DBRX Instruct; 5-shot maj@13 (Table 1) |
| GSM8K | DBRX | 72.8 % | vendor-reported | DBRX Instruct; 5-shot, newer harness commit (Table 2) |
| HellaSwag | DBRX | 89 % | vendor-reported | DBRX Instruct; 10-shot |
| HumanEval | DBRX | 70.1 % | vendor-reported | DBRX Instruct; 0-shot pass@1 |
| MMLU | DBRX | 73.7 % | vendor-reported | DBRX Instruct; 5-shot |
Where this comes from
Every recorded score of this organisation's models, with who ran it. Scores from different settings are not directly comparable.
Sources
- databricks.com/company/about-us https://www.databricks.com/company/about-us
To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Databricks", https://aurion.semai.id/organisations/databricks/, records of October 2026.