Inference
EN
Mistral

Mixtral 8x22B Instruct v0.1

Mixtral 8x22B Instruct v0.1 is a standard model from Mistral in the Mixtral 8x22B family. It has 1 scored result in 1 category. It has no index.

  • Open weights
  • Standard
  • Input: text
  • Released 2024-04
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.15%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.64KMedian 262K
EloLMArena rating and rank.1162±5 #344Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.1 counted24.4—
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.None counted——

Results

1 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Massive Multitask Language UnderstandingKnowledge77.8%27 / 34
MedQAHealthcare62.1% ±0.986 / 95

Sources

BenchLMCC BY-NC 4.0

Questions

What is the context window of Mixtral 8x22B Instruct v0.1?
64K tokens.
Is Mixtral 8x22B Instruct v0.1 open source?
Yes. Its weights are published.
When was Mixtral 8x22B Instruct v0.1 released?
April 2024.

More from Mistral

All models
Mixtral 8x22B InstructUnrankedMistral 7B v0.3UnrankedMistral LargeUnrankedMistral NemoUnrankedMistral Large 227.4