DBRX Base: Complete Benchmark Performance Guide

other dbrx-base 2024-03-27 DBRX Open Model License

In-depth analysis of DBRX Base performance on MMLU, HumanEval, GSM8K, MATH, BBH benchmarks, including pricing and use cases.

Key Specifications

Vendorother
Versiondbrx-base
Release Date2024-03-27
Context Window32768 tokens
Input Modalitiestext
Output Modalitiestext
LicenseDBRX Open Model License
Documentationhttps://huggingface.co/models

Benchmark Performance

Benchmark Score Unit Evaluated At Notes Source
MMLU 79.9 % 2024-03-27 5-shot view
HUMANEVAL 72.1 pass@1 2024-03-27 — view
GSM8K 75.4 % 2024-03-27 0-shot CoT view
MATH 36 % 2024-03-27 0-shot CoT view
BBH 72.3 % 2024-03-27 3-shot CoT view
GPQA 39.3 % 2024-03-27 0-shot view
IFEVAL 79.3 % 2024-03-27 prompt_strict view
ARC 93.3 % 2024-03-27 challenge view
MUSR 53.8 % 2024-03-27 0-shot view
WINOGRANDE 79.8 % 2024-03-27 0-shot view

Pricing

Tier Price Currency
Input$0.75 / MtokUSD
Output$0.75 / MtokUSD
Cache Read$0 / MtokUSD
Cache Write$0 / MtokUSD

Source: https://huggingface.co/models · as of 2024-03-27

Compliance

  • Data Residency: self-host
  • SOC2: ✗
  • HIPAA: ✗
  • GDPR: ✗
  • ISO 27001: ✗

DBRX Base

Model Overview

Databricks DBRX Base 基础 MoE 模型, 32K 上下文, 总参 132B/活跃 36B, 适合企业定制微调。

Core Specifications

Vendor Version Release Date Context Window Input Modalities Output Modalities License
Other dbrx-base 2024-03-27 32K text text DBRX Open Model License

Benchmark Performance

Benchmark Score Unit Notes
MMLU (Massive Multitask Language Understanding) 79.9 % 5-shot
HumanEval 72.1 pass@1 —
GSM8K (Grade School Math 8K) 75.4 % 0-shot CoT
MATH 36.0 % 0-shot CoT
BBH (BIG-Bench Hard) 72.3 % 3-shot CoT
GPQA 39.3 % 0-shot
IFEval 79.3 % prompt_strict
ARC 93.3 % challenge
MUSR 53.8 % 0-shot
WinoGrande 79.8 % 0-shot

Pricing

Input Output Cache Read Cache Write
— — — —

per million tokens

Strengths

  • Mixture-of-Experts architecture.

Weaknesses

  • Proprietary, not self-hostable.

Use Cases

  • Code generation and debugging

References