Back to Models
mistralai logo
mistralai/mixtral-8x22b-instruct
Not Available

Mixtral 8x22B Instruct

Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding, and reasoning - large context length (64k) - fluency in English, French, Italian, German, and Spanish See benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/). #moe

4/17/2024
65,536 tokens
#171 Text (Japanese)
Specifications

Modalities

Input
text
Output
text

Supported Parameters

frequency_penalty
max_tokens
presence_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_p
Leaderboard
Text
🏆OverallELO: 1,229
#249
🇯🇵JapaneseELO: 1,109
#171
🇨🇳ChineseELO: 1,211
#244
🇰🇷KoreanELO: 1,143
#187
🇬🇧EnglishELO: 1,252
#246
frenchELO: 1,260
#176
germanELO: 1,218
#198
spanishELO: 1,227
#189
russianELO: 1,222
#240
💻CodingELO: 1,275
#241
🧮MathELO: 1,227
#229
✍️Creative WritingELO: 1,190
#251
📝Instruction FollowingELO: 1,211
#245
🌶️Hard PromptsELO: 1,242
#245
💬Multi-TurnELO: 1,187
#257