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
#220 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
๐Ÿ†OverallELO: 1,229
#299
๐Ÿ‡ฏ๐Ÿ‡ตJapaneseELO: 1,109
#220
๐Ÿ‡จ๐Ÿ‡ณChineseELO: 1,210
#297
๐Ÿ‡ฐ๐Ÿ‡ทKoreanELO: 1,141
#232
๐Ÿ‡ฌ๐Ÿ‡งEnglishELO: 1,252
#296
frenchELO: 1,252
#229
germanELO: 1,216
#240
spanishELO: 1,224
#236
russianELO: 1,223
#290
๐Ÿ’ปCodingELO: 1,277
#290
๐ŸงฎMathELO: 1,228
#277
โœ๏ธCreative WritingELO: 1,190
#301
๐Ÿ“Instruction FollowingELO: 1,214
#295
๐ŸŒถ๏ธHard PromptsELO: 1,243
#295
๐Ÿ’ฌMulti-TurnELO: 1,188
#307