GeekRadar / The comparison desk
COMPARE.
AI models
mistral

Mistral Small 3.2 (2506)

Model evaluation

Capability & preference

Human preference · Arena

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

Mistral Small 3.2 (2506) 1338.0 Mistral Small 3.2 (2506) · 95% interval 1332.9–1343.2 · 17,462 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

Mistral Small 3.2 (2506)

1,339.87 rating

Confidence interval: 1,322.43 – 1,357.31

1092 votes

Category
chinese
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,362.07 rating

Confidence interval: 1,352.00 – 1,372.14

3337 votes

Category
coding
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,304.35 rating

Confidence interval: 1,291.64 – 1,317.05

2152 votes

Category
creative_writing
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,357.19 rating

Confidence interval: 1,350.23 – 1,364.15

7568 votes

Category
english
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,291.62 rating

Confidence interval: 1,284.38 – 1,298.86

12179 votes

Category
exclude_ties
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,290.87 rating

Confidence interval: 1,271.44 – 1,310.29

856 votes

Category
expert
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,337.01 rating

Confidence interval: 1,297.93 – 1,376.08

227 votes

Category
french
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,340.20 rating

Confidence interval: 1,310.96 – 1,369.43

427 votes

Category
german
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,335.15 rating

Confidence interval: 1,328.26 – 1,342.05

7758 votes

Category
hard_prompts
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,356.86 rating

Confidence interval: 1,347.06 – 1,366.66

3448 votes

Category
hard_prompts_english
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,325.10 rating

Confidence interval: 1,314.18 – 1,336.03

2925 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,303.85 rating

Confidence interval: 1,293.64 – 1,314.06

3146 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,340.11 rating

Confidence interval: 1,323.11 – 1,357.10

1141 votes

Category
industry_legal_and_government
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,338.46 rating

Confidence interval: 1,327.54 – 1,349.39

2899 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,351.27 rating

Confidence interval: 1,333.15 – 1,369.38

994 votes

Category
industry_mathematical
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,345.64 rating

Confidence interval: 1,328.03 – 1,363.25

1128 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,360.29 rating

Confidence interval: 1,352.57 – 1,368.02

5903 votes

Category
industry_software_and_it_services
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,309.88 rating

Confidence interval: 1,300.26 – 1,319.50

3757 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,309.21 rating

Confidence interval: 1,300.36 – 1,318.06

4382 votes

Category
instruction_following
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,275.48 rating

Confidence interval: 1,249.52 – 1,301.44

520 votes

Category
japanese
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,255.51 rating

Confidence interval: 1,223.98 – 1,287.04

362 votes

Category
korean
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,325.72 rating

Confidence interval: 1,315.74 – 1,335.70

3423 votes

Category
longer_query
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,341.03 rating

Confidence interval: 1,323.66 – 1,358.40

1049 votes

Category
math
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,343.43 rating

Confidence interval: 1,332.74 – 1,354.12

2994 votes

Category
multi_turn
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,314.96 rating

Confidence interval: 1,308.63 – 1,321.28

9884 votes

Category
non_english
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,338.05 rating

Confidence interval: 1,332.86 – 1,343.24

17462 votes

Category
overall
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,316.68 rating

Confidence interval: 1,302.06 – 1,331.31

1736 votes

Category
polish
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,323.66 rating

Confidence interval: 1,307.66 – 1,339.66

1232 votes

Category
russian
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

Mistral Small 3.2 (2506)

1,346.79 rating

Confidence interval: 1,317.51 – 1,376.07

419 votes

Category
spanish
Evaluated configuration
Mistral Small 3.2 (2506)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Mistral Small 3.2 (2506)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0