Key Specifications

SpecificationDBRX InstructMixtral 8x22B
Vendorothermistral
Versiondbrx-instruct8x22b
Release Date2024-03-272024-04-10
Context Window32768 tokens64000 tokens
Input Modalitiestexttext
Output Modalitiestexttext
LicenseDBRX Open Model LicenseApache 2.0
SOC2
HIPAA
GDPR
ISO 27001

Benchmark Results

BenchmarkDBRX InstructMixtral 8x22BWinner
ARC93.9DBRX Instruct
BBH71.774.5Mixtral 8x22B
GPQA34.7DBRX Instruct
GSM8K78.778.6DBRX Instruct
HUMANEVAL72.845.2DBRX Instruct
IFEVAL73.1DBRX Instruct
MATH50.146DBRX Instruct
MMLU81.377.8DBRX Instruct
MUSR54.7DBRX Instruct
WINOGRANDE81.8DBRX Instruct

Pricing Comparison

Tier (per Mtok)DBRX InstructMixtral 8x22B
Input$0.75$1.2
Output$0.75$1.2
Cache Read$0$0
Cache Write$0$0

DBRX Instruct karşı Mixtral 8x22B

Model Genel Bakışı

DBRX Instruct and Mixtral 8x22B are both notable options in the AI model market. This page compares their benchmarks, pricing, and compliance.

Temel Özellikler

SatıcıYayın TarihiBağlam PenceresiLisans
Other / Mistral2024-03-27 / 2024-04-1032K / 64KDBRX Open Model License / Apache 2.0

Benchmark Performansı

BenchmarkDBRX InstructMixtral 8x22BKazanan
ARC93.9A
BBH (BIG-Bench Hard)71.774.5B
GPQA34.7A
GSM8K (Grade School Math 8K)78.778.6Tie
HumanEval72.845.2A
IFEval73.1A
MATH50.146.0A
MMLU (Massive Multitask Language Understanding)81.377.8A
MUSR54.7A
WinoGrande81.8A

Fiyat Karşılaştırması

GirişÇıkışÖnbellek OkumaÖnbellek Yazma
— / —— / —— / —— / —

milyon token başına — A / B

Güçlü Yönler & Zayıf Yönler

DBRX Instruct

  • ✅ MMLU score 81.3, strong knowledge reasoning.
  • ✅ 采用 MoE 混合专家架构。
  • ⚠️ 闭源专有模型,不支持自托管。

Mixtral 8x22B

  • ✅ 采用 MoE 混合专家架构。
  • ⚠️ HumanEval 45.2,代码能力较弱。
  • ⚠️ 闭源专有模型,不支持自托管。

Editör Görüşü

DBRX Instruct and Mixtral 8x22B each have their strengths. Choose based on workload (code, long context, vision), referencing the tables above.

SSS

Which model is better for coding tasks?

Refer to the HumanEval benchmark table; the model with a higher score is better suited for coding tasks.

Which model is cheaper?

Refer to the pricing comparison table above; the model with lower input/output prices is more cost-effective.

Which has a longer context window?

Refer to the key specifications table; the model with a larger context window is better for long documents.

Referanslar

Editor's Take

See Editor's Take section.