GeekRadar / The comparison desk
COMPARE.
AI models
mistral

mistral-medium

Model evaluation

Capability & preference

Human preference · Arena

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

mistral-medium 1165.1 mistral-medium · 95% interval 1159.7–1170.5 · 34,550 votes · 2026-10-15

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 · 2026-10-15 · rating

mistral-medium

1,109.07 rating

Confidence interval: 1,095.51 – 1,122.62

3014 votes

Category
chinese
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

mistral-medium

1,161.87 rating

Confidence interval: 1,151.53 – 1,172.21

5149 votes

Category
coding
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

mistral-medium

1,157.55 rating

Confidence interval: 1,146.79 – 1,168.31

5549 votes

Category
creative_writing
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

mistral-medium

1,190.22 rating

Confidence interval: 1,183.81 – 1,196.63

23846 votes

Category
english
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

mistral-medium

1,030.41 rating

Confidence interval: 1,022.46 – 1,038.36

23596 votes

Category
exclude_ties
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

mistral-medium

1,125.12 rating

Confidence interval: 1,108.05 – 1,142.20

1357 votes

Category
expert
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

mistral-medium

1,179.77 rating

Confidence interval: 1,152.47 – 1,207.06

721 votes

Category
french
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

mistral-medium

1,154.69 rating

Confidence interval: 1,132.23 – 1,177.14

852 votes

Category
german
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

mistral-medium

1,149.12 rating

Confidence interval: 1,140.53 – 1,157.72

8650 votes

Category
hard_prompts
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

mistral-medium

1,157.64 rating

Confidence interval: 1,147.91 – 1,167.37

6398 votes

Category
hard_prompts_english
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

mistral-medium

1,119.50 rating

Confidence interval: 1,106.90 – 1,132.10

3224 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

mistral-medium

1,137.77 rating

Confidence interval: 1,127.18 – 1,148.36

5402 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

mistral-medium

1,169.71 rating

Confidence interval: 1,153.33 – 1,186.08

1811 votes

Category
industry_legal_and_government
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

mistral-medium

1,158.25 rating

Confidence interval: 1,147.78 – 1,168.73

6062 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

mistral-medium

1,177.86 rating

Confidence interval: 1,166.54 – 1,189.19

3806 votes

Category
industry_mathematical
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

mistral-medium

1,132.17 rating

Confidence interval: 1,116.07 – 1,148.26

1925 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

mistral-medium

1,153.68 rating

Confidence interval: 1,144.83 – 1,162.54

9016 votes

Category
industry_software_and_it_services
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

mistral-medium

1,172.03 rating

Confidence interval: 1,162.73 – 1,181.34

8402 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

mistral-medium

1,151.64 rating

Confidence interval: 1,143.57 – 1,159.71

11466 votes

Category
instruction_following
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

mistral-medium

1,012.46 rating

Confidence interval: 978.70 – 1,046.22

337 votes

Category
japanese
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

mistral-medium

1,032.10 rating

Confidence interval: 996.38 – 1,067.81

268 votes

Category
korean
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

mistral-medium

1,153.20 rating

Confidence interval: 1,140.44 – 1,165.96

2718 votes

Category
longer_query
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

mistral-medium

1,179.76 rating

Confidence interval: 1,169.03 – 1,190.49

4406 votes

Category
math
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

mistral-medium

1,147.25 rating

Confidence interval: 1,136.00 – 1,158.49

4621 votes

Category
multi_turn
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

mistral-medium

1,128.63 rating

Confidence interval: 1,120.37 – 1,136.88

10704 votes

Category
non_english
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

mistral-medium

1,165.10 rating

Confidence interval: 1,159.68 – 1,170.52

34550 votes

Category
overall
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

mistral-medium

1,167.63 rating

Confidence interval: 1,152.67 – 1,182.59

1757 votes

Category
russian
Evaluated configuration
mistral-medium
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

mistral-medium

1,143.30 rating

Confidence interval: 1,111.21 – 1,175.39

439 votes

Category
spanish
Evaluated configuration
mistral-medium
Evaluation type
human preference

Run it locally

Inference · memory estimate

mistral-medium

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary