GeekRadar / The comparison desk

COMPARE.

AI models

mistral

Mixtral 8x22B Instruct v0.1

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

Mixtral 8x22B Instruct v0.1 1162.0 Mixtral 8x22B Instruct v0.1 · 95% interval 1157.4–1166.5 · 51,416 votes · 2026-10-28

Recorded results

Only the same benchmark, version, workload, scenario and unit share a row. Missing results are not zero. System results include the full submitted hardware and software configuration.

Arena text preference / chinesehuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,116.30 rating

Confidence interval: 1,105.18 – 1,127.42

5655 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,165.32 rating

Confidence interval: 1,156.77 – 1,173.86

8780 votes

Oct 28, 2026

Category: coding
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,141.06 rating

Confidence interval: 1,131.80 – 1,150.31

7447 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,187.14 rating

Confidence interval: 1,181.50 – 1,192.77

29892 votes

Oct 28, 2026

Category: english
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,023.69 rating

Confidence interval: 1,016.73 – 1,030.66

33717 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,112.95 rating

Confidence interval: 1,099.29 – 1,126.61

2582 votes

Oct 28, 2026

Category: expert
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,166.37 rating

Confidence interval: 1,140.43 – 1,192.31

767 votes

Oct 28, 2026

Category: french
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,141.23 rating

Confidence interval: 1,123.85 – 1,158.61

1653 votes

Oct 28, 2026

Category: german
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,149.60 rating

Confidence interval: 1,142.68 – 1,156.52

14707 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,162.95 rating

Confidence interval: 1,154.70 – 1,171.20

9466 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,118.56 rating

Confidence interval: 1,108.45 – 1,128.68

5554 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,138.58 rating

Confidence interval: 1,129.68 – 1,147.48

7616 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,165.11 rating

Confidence interval: 1,151.57 – 1,178.66

2798 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,150.96 rating

Confidence interval: 1,141.94 – 1,159.97

8677 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,179.00 rating

Confidence interval: 1,169.49 – 1,188.51

6001 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,119.73 rating

Confidence interval: 1,106.02 – 1,133.44

2823 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,154.02 rating

Confidence interval: 1,146.74 – 1,161.31

14389 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,160.98 rating

Confidence interval: 1,153.41 – 1,168.54

12808 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,146.98 rating

Confidence interval: 1,140.51 – 1,153.45

18515 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,036.78 rating

Confidence interval: 1,015.17 – 1,058.40

972 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,056.60 rating

Confidence interval: 1,034.55 – 1,078.65

1187 votes

Oct 28, 2026

Category: korean
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,143.45 rating

Confidence interval: 1,133.71 – 1,153.20

5865 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,184.27 rating

Confidence interval: 1,175.32 – 1,193.22

6778 votes

Oct 28, 2026

Category: math
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,130.15 rating

Confidence interval: 1,121.17 – 1,139.13

7764 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,128.08 rating

Confidence interval: 1,121.86 – 1,134.29

21524 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,161.96 rating

Confidence interval: 1,157.45 – 1,166.48

51416 votes

Oct 28, 2026

Category: overall
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,170.91 rating

Confidence interval: 1,110.51 – 1,231.31

132 votes

Oct 28, 2026

Category: polish
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,157.57 rating

Confidence interval: 1,147.37 – 1,167.77

4914 votes

Oct 28, 2026

Category: russian
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

Mixtral 8x22B Instruct v0.1

1,150.65 rating

Confidence interval: 1,125.14 – 1,176.17

826 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: Mixtral 8x22B Instruct v0.1
Evaluation type: human preference

Run it locally

Inference · memory estimate

Mixtral 8x22B Instruct v0.1

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Apache 2.0