Noometry

Mistral AI, open weights

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.

Last verified

Noometry rank
#333 of 354
Index score
27.1
Evidence
Confirmed 34 results
Provider
Mistral AI
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

Category scores

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

  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
CategoryScoreRankResults
Coding24.2#3294
Agentic & Tool Use23.1#1271
Reasoning19.9#2482
Math22.9#2753
Knowledge15.1#2934
Multilingual32.8#2551
Instruction Following57.7#2662
Long Context34.7#2471
Writing & Preference36.9#2624

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

CategoryScorevs medianRank
Reasoning19.9−3.7#248 of 350, top 71%
Agentic & Tool Use23.1−7.3#127 of 154, top 83%
Long Context34.7−6.3#247 of 296, top 84%

Weakest categories

CategoryScorevs medianRank
Coding24.2−14.5#329 of 340, top 97%
Knowledge15.1−22.2#293 of 314, top 94%
Instruction Following57.7−13.6#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.

ModelRankScoreBlended $/MSpeed
Yi-34B#32927.8——Compare
Llama 4 Scout#33027.7$0.15272Compare
Llama 3.2 90B#33127.5——Compare
Gemini 1.0 Pro#33227.3——Compare
Mixtral 8x7B#33427.1$0.70—Compare
Qwen Turbo#33527.1$0.0875—Compare
Qwen3-1.7B#33626.6——Compare
Mistral Nemo#33726.4$0.15—Compare

Sponsored placements are available on pages like this one. Advertise on Noometry

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

BenchmarkScorePositionSettingSourceDate
WeirdML3.2%#118 of 119, top 100%Epoch AI
BigCodeBench Instruct40.6%#32 of 64, top 50%BigCodeBench2024-04-17
LMArena Coding1166#252 of 294, top 86%LMArena2026-10-08
BigCodeBench Complete50.2%#33 of 66, top 50%BigCodeBench2024-04-17
BigCodeBench Complete45.3%BigCodeBench2024-04-17
HumanEval+72%#18 of 45, top 40%EvalPlus
MBPP+64.3%#20 of 38, top 53%EvalPlus

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
Cybench7.5%#20 of 21, top 96%Epoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
LMArena Hard Prompts1150#253 of 297, top 86%LMArena2026-10-08
DTBench55.1%#122 of 151, top 81%Epoch AI
Epoch Capabilities Index122.03#163 of 213, top 77%Epoch AI2024-04-17
ForecastBench56.3#64 of 72, top 89%Epoch AI

Math

BenchmarkScorePositionSettingSourceDate
Omni-MATH16.3%#52 of 57, top 92%HELM Capabilities
LMArena Math1184#238 of 285, top 84%LMArena2026-10-08
MATH Level 524.2%#59 of 79, top 75%Epoch AI2025-01-27

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond34.1%#160 of 186, top 87%Epoch AI2025-01-27
MMLU-Pro46%#52 of 58, top 90%HELM Capabilities
GPQA (HELM)33.4%#50 of 57, top 88%HELM Capabilities
LMArena Expert1113#248 of 273, top 91%LMArena2026-10-08
MMLU77.8%#27 of 81, top 34%Epoch AI

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1128#255 of 297, top 86%LMArena2026-10-08
LMArena Chinese1116#254 of 285, top 90%LMArena2026-10-08
LMArena French1166#201 of 223, top 91%LMArena2026-10-08
LMArena German1141#204 of 231, top 89%LMArena2026-10-08
LMArena Japanese1037#193 of 211, top 92%LMArena2026-10-08
LMArena Korean1057#191 of 213, top 90%LMArena2026-10-08
LMArena Russian1158#249 of 283, top 88%LMArena2026-10-08
LMArena Spanish1151#205 of 226, top 91%LMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
IFEval72.4%#55 of 57, top 97%HELM Capabilities
LMArena Instruction Following1147#254 of 298, top 86%LMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1144#256 of 291, top 88%LMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1162#256 of 297, top 87%LMArena2026-10-08
LMArena Creative Writing1141#254 of 295, top 87%LMArena2026-10-08
WildBench71.1%#51 of 57, top 90%HELM Capabilities
LMArena Multi-Turn1130#257 of 295, top 88%LMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
mistral$2$6—2026-10-10
openrouter$2$6$0.202026-10-10

All Mistral AI API prices → Estimate your cost →

Compare Mixtral 8x22B

Other Mistral AI models

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.