DBRX Instruct — benchmark results
Provider: Databricks. Released 2024-03-27. Access: Open.
Unified ELO 1248 ± 38, rank #1621 of 1776 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Humanity's Last Exam | 6.59 | Accuracy (%) | 48.4 |
| HELM Lite | 32.55 | Mean win rate (self-reported) | 26 |
| HELM (Stanford) | 28.87 | Mean Win Rate (%) | 21.1 |
| HELM Safety BBQ | 79.2 | BBQ accuracy (%) | 18.6 |
| HELM NaturalQuestions (Closed) | 28.39 | F1 (%) | 15.6 |
| HELM WMT 2014 | 13.12 | BLEU-4 (%) | 12.2 |
| AA SciCode | 11.81 | Accuracy (%) | 12 |
| AA GPQA Diamond | 33.13 | Accuracy (%) | 11.3 |
| HELM NarrativeQA | 48.84 | F1 (%) | 7.8 |
| AA MMLU-Pro | 39.71 | Accuracy (%) | 7.3 |
| Artificial Analysis Intelligence Index | 2.96 | Intelligence Index | 7.1 |
| AA LiveCodeBench | 9.31 | Pass@1 (%) | 6.4 |
Interactive version: theaggregate.ai/model?slug=dbrx-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.