HomeDBRX-Instruct
132B
Model parameter quantity
DataBricks
Affiliated organization
Open Source
License Type
March 26, 2024
Release time
Model Introduction
DBRX-Instruct is an MoE model trained from scratch by DataBricks, utilizing a selection scheme of 16 experts choosing 4, with an active parameter count of 36B. It's pretrained on 12T tokens, supporting a 32K context.
Comprehensive score
Language dialogue
Knowledge reserve
Reasoning association
Mathematical calculation
Code writing
Command following
Swipe left and right to view more
Language comprehension ability
Often makes semantic misjudgments, leading to obvious logical disconnects in responses.
3.8
Knowledge coverage scope
Has significant knowledge blind spots, often showing factual errors and repeating outdated information.
5.9
Reasoning ability
Unable to maintain coherent reasoning chains, often causing inverted causality or miscalculations.
2.6
Model comparison
DBRX-Instruct vs Doubao-Seed-1.6-251015 (Thinking)
The deep reasoning model released by ByteDance, which supports manual switching of deep reasoning, and its performance is significantly improved compared to doubao-1.5.
DBRX-Instruct vs Doubao-Seed-1.6-thinking-250715
The latest version of the seed series model launched by ByteDance, which supports the thinking mode.
Related model
DBRX-Instruct
DBRX-Instruct is an MoE model trained from scratch by DataBricks, utilizing a selection scheme of 16 experts choosing 4, with an active parameter count of 36B. It's pretrained on 12T tokens, supporting a 32K context.
Doubao-Seed-1.6-251015 (Thinking)
The deep reasoning model released by ByteDance, which supports manual switching of deep reasoning, and its performance is significantly improved compared to doubao-1.5.
Doubao-Seed-1.6-thinking-250715
The latest version of the seed series model launched by ByteDance, which supports the thinking mode.
ERNIE 5.0
Baidu’s newly released ERNIE large model, version 5.0.
Spark-X1
The inference model Spark X1 released by iFlytek, on the basis of leading domestic mathematical tasks, benchmarks the performance of general tasks such as inference, text generation, and language understanding against OpenAI o1 and DeepSeek R1.
Relevant documents
DeepMind CEO Hassabis: I sleep six hours a day, usually feel energetic around 1 a.m.
Fortune recently featured an interview with Demis Hassabis, CEO of Google DeepMind, revealing his unconventional approach to rest and productivity. Hassabis disclosed that he sleeps very little, structuring his waking hours into two distinct work blo
OpenAI, Anthropic Vie for Market Share Despite Revenue Shortfalls
Despite recent reports suggesting OpenAI missed revenue targets, creating pressure on tech stocks this Tuesday, private AI lab investors remain resilient. Seasoned backers have confirmed they will not reduce investment despite negative media coverage
California AV Compliance: A New Era of Tickets, Geofences, and 1M Miles
Guident operates an AuveTech shuttle in South Florida, managing a four-mile route in West Palm Beach and a one-mile route in Boca Raton using its remote monitoring technology. | Credit: GuidentCalifornia is redefining the regulatory landscape for dri
Apple Smart Glasses Could Debut at WWDC27, Highlighting Privacy Protection
Bloomberg’s Mark Gurman reports that Apple’s smart glasses, codenamed N50, are slated for a WWDC27 debut in June 2027, with a retail launch expected in autumn 2027. Originally targeted for late this year and early 2027, the device’s release has been
Inside Details Exposed About Next-Gen Gemini: Strained Computing Power, Internal Teams Disagreed on Development Priorities and Resource Allocation
Reports indicate that the launch of Google’s highly anticipated next-generation Gemini model has been pushed back. Internal disagreements over development priorities and resource allocation, combined with limited computing capacity and complex approv
