dbrx-base: benchmark results
Provider: Databricks. Access: Open.
Unified ELO 1528 ± 20, rank #1000 of 2928 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - MMLU | 74.7 | Accuracy (%) (5-shot) | 96.2 |
| Open LLM Leaderboard v1 - HellaSwag | 89 | Normalized accuracy (%) (10-shot) | 95.8 |
| Open LLM Leaderboard v1 - GSM8K | 68.54 | Accuracy (%) (5-shot) | 86.2 |
| Open LLM Leaderboard - GPQA | 32.67 | Score | 79 |
| Open LLM Leaderboard v1 - ARC Challenge | 66.04 | Normalized accuracy (%) (25-shot) | 72.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.07 | MC2 (%) (0-shot) | 64.1 |
| Open LLM Leaderboard v1 - WinoGrande | 78.06 | Accuracy (%) (5-shot) | 60.4 |
| Open LLM Leaderboard - BBH | 51.96 | Score | 58.9 |
| Open LLM Leaderboard - MMLU-Pro | 35 | Score | 51.4 |
| Open LLM Leaderboard - MATH Level 5 | 10 | Score | 47.5 |
| Open LLM Leaderboard - MuSR | 40.67 | Score | 47.3 |
| Open LLM Leaderboard - IFEval | 8.21 | Score | 1.4 |
Interactive version: theaggregate.ai/model?slug=dbrx-base · How It Works · Data refreshed daily, snapshot 2026-09-23.