Mistral AI, open weights

# Mixtral 8x22B

> Mixtral 8x22B by Mistral AI, released April 2024. Ranked #333 of 354 with a Noometry Index of 27.1. API: $2 in / $6 out per M tokens. 64K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/mixtral-8x22b
- Last updated: 2026-10-10
- Title: Mixtral 8x22B Benchmarks, Price & Rank (October 2026)

Mixtral 8x22B by Mistral AI ranks 333rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 27.1. Its strongest category is agentic & tool use, where it ranks 127th. API pricing starts at $2 per million input tokens and $6 per million output tokens, with a 64K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #333 of 354
- **Index score:** 27.1
- **Evidence:** Confirmed 34 results
- **Provider:** [![](/logos/mistral.svg) Mistral AI](https://noometry.com/providers/mistral)
- **Released:** April 17, 2024
- **Weights:** Open weights
- **Reasoning:** No
- **Context window:** 64K
- **Max output:** 64K
- **Input price:** $2 / M
- **Output price:** $6 / M
- **Blended price:** $3 / M
- **Output speed:** Not measured
- **Value:** #187 of 219
- **Knowledge cutoff:** April 2024
- **Input:** text
- **Hugging Face:** [mistralai/Mixtral-8x22B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x22B-Instruct-v0.1)

## Category scores

Each category score combines every public result we have in that category.

Mixtral 8x22B category scores

1.  Coding 24.2
2.  Agentic & Tool Use 23.1
3.  Reasoning 19.9
4.  Math 22.9
5.  Knowledge 15.1
6.  Multilingual 32.8
7.  Instruction Following 57.7
8.  Long Context 34.7
9.  Writing & Preference 36.9
10.  0204060

Mixtral 8x22B category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 24.2 | #329 | 4 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 23.1 | #127 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 19.9 | #248 | 2 |
| [Math](https://noometry.com/best/math) | 22.9 | #275 | 3 |
| [Knowledge](https://noometry.com/best/knowledge) | 15.1 | #293 | 4 |
| [Multilingual](https://noometry.com/best/multilingual) | 32.8 | #255 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 57.7 | #266 | 2 |
| [Long Context](https://noometry.com/best/long-context) | 34.7 | #247 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 36.9 | #262 | 4 |

## Strengths and weaknesses

Categories where Mixtral 8x22B places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Mixtral 8x22B: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Reasoning](https://noometry.com/best/reasoning) | 19.9 | −3.7 | #248 of 350, top 71% |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 23.1 | −7.3 | #127 of 154, top 83% |
| [Long Context](https://noometry.com/best/long-context) | 34.7 | −6.3 | #247 of 296, top 84% |

### Weakest categories

Mixtral 8x22B: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 24.2 | −14.5 | #329 of 340, top 97% |
| [Knowledge](https://noometry.com/best/knowledge) | 15.1 | −22.2 | #293 of 314, top 94% |
| [Instruction Following](https://noometry.com/best/instruction-following) | 57.7 | −13.6 | #266 of 305, top 88% |

## Closest competitors

The models ranked just above and below Mixtral 8x22B. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Mixtral 8x22B
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [Yi-34B](https://noometry.com/models/yi-34b) | #329 | 27.8 | — | — | [Compare](https://noometry.com/compare/mixtral-8x22b-vs-yi-34b) |
| [Llama 4 Scout](https://noometry.com/models/llama-4-scout) | #330 | 27.7 | $0.15 | 272 | [Compare](https://noometry.com/compare/llama-4-scout-vs-mixtral-8x22b) |
| [Llama 3.2 90B](https://noometry.com/models/llama-3-2-90b) | #331 | 27.5 | — | — | [Compare](https://noometry.com/compare/llama-3-2-90b-vs-mixtral-8x22b) |
| [Gemini 1.0 Pro](https://noometry.com/models/gemini-1-0-pro) | #332 | 27.3 | — | — | [Compare](https://noometry.com/compare/gemini-1-0-pro-vs-mixtral-8x22b) |
| [Mixtral 8x7B](https://noometry.com/models/mixtral-8x7b) | #334 | 27.1 | $0.70 | — | [Compare](https://noometry.com/compare/mixtral-8x22b-vs-mixtral-8x7b) |
| [Qwen Turbo](https://noometry.com/models/qwen-turbo) | #335 | 27.1 | $0.0875 | — | [Compare](https://noometry.com/compare/mixtral-8x22b-vs-qwen-turbo) |
| [Qwen3-1.7B](https://noometry.com/models/qwen3-1-7b) | #336 | 26.6 | — | — | [Compare](https://noometry.com/compare/mixtral-8x22b-vs-qwen3-1-7b) |
| [Mistral Nemo](https://noometry.com/models/mistral-nemo) | #337 | 26.4 | $0.15 | — | [Compare](https://noometry.com/compare/mistral-nemo-vs-mixtral-8x22b) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Mixtral 8x22B Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 3.2% | #118 of 119, top 100% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [BigCodeBench Instruct](https://noometry.com/benchmarks/bigcodebench-instruct) | 40.6% | #32 of 64, top 50% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-04-17 |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1166 | #252 of 294, top 86% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 50.2% | #33 of 66, top 50% |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-04-17 |
| [BigCodeBench Complete](https://noometry.com/benchmarks/bigcodebench-complete) | 45.3% |  |  | [BigCodeBench](https://bigcode-bench.github.io/) | 2024-04-17 |
| [HumanEval+](https://noometry.com/benchmarks/humaneval-plus) | 72% | #18 of 45, top 40% |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |
| [MBPP+](https://noometry.com/benchmarks/mbpp-plus) | 64.3% | #20 of 38, top 53% |  | [EvalPlus](https://evalplus.github.io/leaderboard.html) |  |

### Agentic & Tool Use

Mixtral 8x22B Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Cybench](https://noometry.com/benchmarks/cybench) | 7.5% | #20 of 21, top 96% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

Mixtral 8x22B Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1150 | #253 of 297, top 86% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 55.1% | #122 of 151, top 81% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 122.03 | #163 of 213, top 77% |  | [Epoch AI](https://epoch.ai/eci) | 2024-04-17 |
| [ForecastBench](https://noometry.com/benchmarks/forecastbench) | 56.3 | #64 of 72, top 89% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Math

Mixtral 8x22B Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [Omni-MATH](https://noometry.com/benchmarks/omni-math) | 16.3% | #52 of 57, top 92% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1184 | #238 of 285, top 84% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MATH Level 5](https://noometry.com/benchmarks/math-level-5) | 24.2% | #59 of 79, top 75% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |

### Knowledge

Mixtral 8x22B Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 34.1% | #160 of 186, top 87% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2025-01-27 |
| [MMLU-Pro](https://noometry.com/benchmarks/mmlu-pro) | 46% | #52 of 58, top 90% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [GPQA (HELM)](https://noometry.com/benchmarks/helm-gpqa) | 33.4% | #50 of 57, top 88% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1113 | #248 of 273, top 91% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [MMLU](https://noometry.com/benchmarks/mmlu) | 77.8% | #27 of 81, top 34% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Multilingual

Mixtral 8x22B Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1128 | #255 of 297, top 86% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1116 | #254 of 285, top 90% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1166 | #201 of 223, top 91% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1141 | #204 of 231, top 89% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Japanese](https://noometry.com/benchmarks/arena-japanese) | 1037 | #193 of 211, top 92% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1057 | #191 of 213, top 90% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1158 | #249 of 283, top 88% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1151 | #205 of 226, top 91% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Mixtral 8x22B Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [IFEval](https://noometry.com/benchmarks/ifeval) | 72.4% | #55 of 57, top 97% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1147 | #254 of 298, top 86% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Mixtral 8x22B Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1144 | #256 of 291, top 88% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Mixtral 8x22B Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1162 | #256 of 297, top 87% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1141 | #254 of 295, top 87% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [WildBench](https://noometry.com/benchmarks/wildbench) | 71.1% | #51 of 57, top 90% |  | [HELM Capabilities](https://crfm.stanford.edu/helm/capabilities/latest/) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1130 | #257 of 295, top 88% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

Mixtral 8x22B API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [mistral](https://docs.mistral.ai/getting-started/models/) | $2 | $6 | — | 2026-10-10 |
| [openrouter](https://openrouter.ai/mistralai/mixtral-8x22b-instruct) | $2 | $6 | $0.20 | 2026-10-10 |

[All Mistral AI API prices →](https://noometry.com/llm-pricing/mistral) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare Mixtral 8x22B

-   [Mixtral 8x22B vs Mixtral 8x7B](https://noometry.com/compare/mixtral-8x22b-vs-mixtral-8x7b)
-   [Mixtral 8x22B vs Gemini 1.0 Pro](https://noometry.com/compare/gemini-1-0-pro-vs-mixtral-8x22b)
-   [Mixtral 8x22B vs Llama 3.2 90B](https://noometry.com/compare/llama-3-2-90b-vs-mixtral-8x22b)
-   [Mixtral 8x22B vs Qwen Turbo](https://noometry.com/compare/mixtral-8x22b-vs-qwen-turbo)
-   [Mixtral 8x22B vs Llama 4 Scout](https://noometry.com/compare/llama-4-scout-vs-mixtral-8x22b)
-   [Mixtral 8x22B vs Qwen3-1.7B](https://noometry.com/compare/mixtral-8x22b-vs-qwen3-1-7b)
-   [Mixtral 8x22B vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-mixtral-8x22b)
-   [Mixtral 8x22B vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-mixtral-8x22b)
-   [Mixtral 8x22B vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-mixtral-8x22b)
-   [Mixtral 8x22B vs Kimi K3](https://noometry.com/compare/kimi-k3-vs-mixtral-8x22b)
-   [Mixtral 8x22B vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-mixtral-8x22b)
-   [Mixtral 8x22B vs Qwen3.8 Max](https://noometry.com/compare/mixtral-8x22b-vs-qwen3-8-max)
-   [Mixtral 8x22B vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-mixtral-8x22b)
-   [Mixtral 8x22B vs Muse Spark 1.3](https://noometry.com/compare/mixtral-8x22b-vs-muse-spark-1-3)

## Other Mistral AI models

-   [Mistral Large 4](https://noometry.com/models/mistral-large-4)43.1
-   [Mistral Medium 3.5](https://noometry.com/models/mistral-medium-3-5)40.2
-   [Mistral Large 3](https://noometry.com/models/mistral-large-3)39.1
-   [Mistral Medium](https://noometry.com/models/mistral-medium)36.3
-   [Magistral Medium](https://noometry.com/models/magistral-medium)35.2
-   [Devstral Small 2505](https://noometry.com/models/devstral-small)34.3
-   [Mistral Small](https://noometry.com/models/mistral-small)33.4
-   [Pixtral Large](https://noometry.com/models/pixtral-large)32.2

## Frequently asked questions

### How good is Mixtral 8x22B?

Mixtral 8x22B by Mistral AI ranks 333rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 27.1. Its strongest category is agentic & tool use, where it ranks 127th. API pricing starts at $2 per million input tokens and $6 per million output tokens, with a 64K-token context window.

### How much does Mixtral 8x22B cost?

Mixtral 8x22B costs $2 per million input tokens and $6 per million output tokens on Mistral AI's own API.

### What is Mixtral 8x22B's context window?

Mixtral 8x22B accepts up to 64K tokens of input and can write up to 64K tokens in one response.

### Is Mixtral 8x22B open source?

Yes. Mixtral 8x22B's weights are downloadable from Hugging Face (mistralai/Mixtral-8x22B-Instruct-v0.1); check the license for commercial terms.

### What are Mixtral 8x22B's strengths and weaknesses?

Relative to other ranked models, Mixtral 8x22B places best in reasoning, agentic & tool use, long context and lowest in coding, knowledge, instruction following.

### What is Mixtral 8x22B best at?

Its best category is agentic & tool use, where it ranks 127th on Noometry.

### Cite this page

Noometry. (2026). Mixtral 8x22B benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/mixtral-8x22b

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/mixtral-8x22b.md).