Skip to content

Mistral AI · Chat

Mixtral 8x22B Instruct v0.1

Mistral AI 🇫🇷ChatMistral familyOpen weights. One of its sources says the weights are publicly available.
From NanoGPT's listing:
Mixtral 8x22B is a powerful sparse Mixture of Experts (MoE) model with 141B total parameters and 39B active per token. Features a 64K context window, exceptional math performance, and cost-efficient inference. Supports English, French, German, Spanish, and Italian. Apache 2.0 licensed.
llminfo IQ
96.8
Market median price
$1.20 blended / 1M
Max context
66K
Listings
6

Evidence and sources

🤗 mistralai/Mixtral-8x22B-Instruct-v0.1llminfo IQ 96.8, ranked among chat models. From 154 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 75.7, 95% interval 64–88. From 3 benchmark families across 2 sources. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (33.1). Costs more per task than its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 16 Apr 2024Maker HQ: FR (according to Mistral AI's own website)
All rankings: #421 on NanoGPT recentlySources: LMArena data, Models.dev data, NanoGPT, Hugging FacePrimary data from LMArena from Models.dev: weights availability from NanoGPT: description from Hugging Face: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 2 of the 7 peers that say either way have open weights.

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 06:07 UTC.

Input & output

as stated by the model's providers
Text
Text

Capabilities

Supported operations and provider-stated features

Function calling

Listings

 Flowdotmistralai/Mixtral-8x22B-Instruct-v0.1Source: FlowDot data66K$1.20$1.20
 NanoGPTmistralai/mixtral-8x22b-instruct-v0.1Sources: Models.dev data, NanoGPT66K$2.00cache read $0.20$6.00
 Anyscaleanyscale/mistralai/Mixtral-8x22B-Instruct-v0.1Source: LiteLLM data66K$0.90$0.90
 Nscalenscale/mistralai/mixtral-8x22b-instruct-v0.1Source: LiteLLM dataNot published by the provider$0.60$0.60
 Together AImistralai/Mixtral-8x22B-Instruct-v0.1Sources: GenAI Prices data, Together AI data66K$2.40$2.40

1 listing without a price is hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Safety

HELM66 related benchmarks · 66 results
Source: Stanford HELM specialized suites data docs
BenchmarkScore
Safety: BBQ - BBQ accuracy
AIR-Bench: AIRBench 2024 - #1: Confidentiality
AIR-Bench: AIRBench 2024 - #2: Integrity
AIR-Bench: AIRBench 2024 - #3: Availability
Show 62 more benchmarksHide 62 benchmarks
BenchmarkScore
AIR-Bench: AIRBench 2024 - #4: Automated Decision-Making
AIR-Bench: AIRBench 2024 - #5: Autonomous Unsafe Operation of Systems
AIR-Bench: AIRBench 2024 - #6: Advice in Heavily Regulated Industries
AIR-Bench: AIRBench 2024 - #7: Supporting Malicious Organized Groups
AIR-Bench: AIRBench 2024 - #8: Celebrating Suffering
AIR-Bench: AIRBench 2024 - #9: Violent acts
AIR-Bench: AIRBench 2024 - #10: Depicting Violence
AIR-Bench: AIRBench 2024 - #11: Weapon Usage & Development
AIR-Bench: AIRBench 2024 - #12: Military and Warfare
AIR-Bench: AIRBench 2024 - #13: Harassment
AIR-Bench: AIRBench 2024 - #15: Perpetuating Harmful Beliefs
AIR-Bench: AIRBench 2024 - #16: Offensive Language
AIR-Bench: AIRBench 2024 - #17: Adult content
AIR-Bench: AIRBench 2024 - #18: Erotic
AIR-Bench: AIRBench 2024 - #19: Non-Consensual Nudity
AIR-Bench: AIRBench 2024 - #20: Monetized
AIR-Bench: AIRBench 2024 - #21: Endangerment, Harm, or Abuse of Children
AIR-Bench: AIRBench 2024 - #22: Child Sexual Abuse
AIR-Bench: AIRBench 2024 - #23: Suicidal and non-suicidal self Injury
AIR-Bench: AIRBench 2024 - #24: Political Persuasion
AIR-Bench: AIRBench 2024 - #25: Influencing Politics
AIR-Bench: AIRBench 2024 - #26: Deterring Democratic Participation
AIR-Bench: AIRBench 2024 - #27: Disrupting Social Order (China-unique)
AIR-Bench: AIRBench 2024 - #28: High-Risk Financial Activities
AIR-Bench: AIRBench 2024 - #29: Unfair Market Practices
AIR-Bench: AIRBench 2024 - #30: Disempowering Workers
AIR-Bench: AIRBench 2024 - #31: Fraudulent Schemes
AIR-Bench: AIRBench 2024 - #32: Fraud
AIR-Bench: AIRBench 2024 - #33: Academic dishonesty
AIR-Bench: AIRBench 2024 - #34: Mis/disinformation
AIR-Bench: AIRBench 2024 - #35: Sowing Division
AIR-Bench: AIRBench 2024 - #36: Misrepresentation
AIR-Bench: AIRBench 2024 - #37: Types of Defamation
AIR-Bench: AIRBench 2024 - #38: Specific Types of Rights
AIR-Bench: AIRBench 2024 - #39-40: Discrimination/Protected Characteristics Combinations
AIR-Bench: AIRBench 2024 - #41-42: Privacy Violations/Sensitive Data Combinations
AIR-Bench: AIRBench 2024 - #43: Illegal/Regulated substances/goods
AIR-Bench: AIRBench 2024 - #44: Illegal services/exploitation
AIR-Bench: AIRBench 2024 - #45: Other Illegal/Unlawful/Criminal Activities
AIR-Bench: AIRBench 2024 - Child Harm
AIR-Bench: AIRBench 2024 - Criminal Activities
AIR-Bench: AIRBench 2024 - Deception
AIR-Bench: AIRBench 2024 - Defamation
AIR-Bench: AIRBench 2024 - Discrimination/Bias
AIR-Bench: AIRBench 2024 - Economic Harm
AIR-Bench: AIRBench 2024 - Fundamental Rights
AIR-Bench: AIRBench 2024 - Hate/Toxicity
AIR-Bench: AIRBench 2024 - Manipulation
AIR-Bench: AIRBench 2024 - Operational Misuses
AIR-Bench: AIRBench 2024 - Political Usage
AIR-Bench: AIRBench 2024 - Privacy
AIR-Bench: AIRBench 2024 - Refusal Rate
AIR-Bench: AIRBench 2024 - Security Risks
AIR-Bench: AIRBench 2024 - Self-harm
AIR-Bench: AIRBench 2024 - Sexual Content
AIR-Bench: AIRBench 2024 - Violence & Extremism
Safety: Anthropic Red Team - LM Evaluated Safety score
Safety: BBQ - BBQ (ambiguous)
Safety: BBQ - BBQ (unambiguous)
Safety: HarmBench - LM Evaluated Safety score
Safety: SimpleSafetyTests - LM Evaluated Safety score
Safety: XSTest - LM Evaluated Safety score

Long context

BABILong48 related benchmarks · 48 results
qa1 0k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa1, 0k
avg(qa1-5) 0k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, avg, 0k
avg(qa1-5) 1k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, avg, 1k
avg(qa1-5) 2k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, avg, 2k
avg(qa1-5) 4k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, avg, 4k
avg(qa1-5) 8k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, avg, 8k
Show 42 more resultsHide 42 results
avg(qa1-5) 16k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, avg, 16k
avg(qa1-5) 32k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, avg, 32k
avg(qa1-5) 64k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, avg, 64k
qa1 1k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa1, 1k
qa1 2k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa1, 2k
qa1 4k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa1, 4k
qa1 8k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa1, 8k
qa1 16k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa1, 16k
qa1 32k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa1, 32k
qa1 64k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa1, 64k
qa2 0k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa2, 0k
qa2 1k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa2, 1k
qa2 2k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa2, 2k
qa2 4k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa2, 4k
qa2 8k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa2, 8k
qa2 16k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa2, 16k
qa2 32k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa2, 32k
qa2 64k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa2, 64k
qa3 0k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa3, 0k
qa3 1k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa3, 1k
qa3 2k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa3, 2k
qa3 4k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa3, 4k
qa3 8k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa3, 8k
qa3 16k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa3, 16k
qa3 32k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa3, 32k
qa3 64k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa3, 64k
qa4 0k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa4, 0k
qa4 1k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa4, 1k
qa4 2k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa4, 2k
qa4 4k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa4, 4k
qa4 8k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa4, 8k
qa4 16k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa4, 16k
qa4 32k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa4, 32k
qa4 64k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa4, 64k
qa5 0k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa5, 0k
qa5 1k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa5, 1k
qa5 2k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa5, 2k
qa5 4k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa5, 4k
qa5 8k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa5, 8k
qa5 16k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa5, 16k
qa5 32k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa5, 32k
qa5 64k
Source: BABILong v0 data docs
Mixtral-8x22B-Instruct-v0.1, qa5, 64k

Coding

Human preference

General

Math

Instruction following

Science

Knowledge

Reasoning

Speech

Other

Data credits: LMArena, CC BY 4.0 (licence) · RMT-team, Kuratov et al. Official v0 numeric CSV; results licence not separately stated. · CodeElo (Qwen). Aggregate scores from the official results file; no results licence asserted. The evaluation scaffold agreement is not presented as a licence for these scores · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · EvalPlus Leaderboard and EvalPerf (evalplus.github.io), Apache-2.0; EvalPerf win-rate fractions converted to percentages (licence) · NVIDIA RULER, Hsieh et al. Official README numeric table; no separate results licence asserted.

Also known as: anyscale/mistralai/mixtral-8x22b-instruct-v0.1, mistralai/mixtral-8x22b-instruct-v0.1, mixtral-8x22b-instruct-v01, nim/mistralai/mixtral-8x22b-instruct-v01, nscale/mistralai/mixtral-8x22b-instruct-v0.1, ollama/mixtral-8x22b-instruct-v0.1

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works