GeekRadar / The comparison desk
COMPARE.
AI models
mistral

Mistral Small 3.1 24B Instruct (2503)

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 3.1 24B Instruct (2503) 1277.1 Mistral Small 3.1 24B Instruct (2503) · 95% interval 1272.5–1281.6 · 32,710 votes · 2026-11-06

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 · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,252.47 rating

Confidence interval: 1,239.16 – 1,265.78

2229 votes

Category
chinese
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,308.87 rating

Confidence interval: 1,300.98 – 1,316.76

6109 votes

Category
coding
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,251.86 rating

Confidence interval: 1,242.41 – 1,261.32

4111 votes

Category
creative_writing
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,294.62 rating

Confidence interval: 1,288.77 – 1,300.47

14245 votes

Category
english
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,203.03 rating

Confidence interval: 1,196.64 – 1,209.42

23328 votes

Category
exclude_ties
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,257.22 rating

Confidence interval: 1,242.21 – 1,272.23

1681 votes

Category
expert
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,272.83 rating

Confidence interval: 1,243.80 – 1,301.86

457 votes

Category
french
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,266.37 rating

Confidence interval: 1,245.31 – 1,287.43

876 votes

Category
german
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,277.67 rating

Confidence interval: 1,271.82 – 1,283.51

14619 votes

Category
hard_prompts
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,289.78 rating

Confidence interval: 1,282.01 – 1,297.54

6524 votes

Category
hard_prompts_english
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,257.16 rating

Confidence interval: 1,248.52 – 1,265.80

5507 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,250.14 rating

Confidence interval: 1,242.05 – 1,258.23

5818 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,270.16 rating

Confidence interval: 1,257.05 – 1,283.26

2118 votes

Category
industry_legal_and_government
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,264.73 rating

Confidence interval: 1,255.95 – 1,273.50

5224 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,270.86 rating

Confidence interval: 1,257.36 – 1,284.35

1932 votes

Category
industry_mathematical
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,267.34 rating

Confidence interval: 1,253.05 – 1,281.63

1948 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,301.33 rating

Confidence interval: 1,294.92 – 1,307.73

10898 votes

Category
industry_software_and_it_services
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,268.31 rating

Confidence interval: 1,260.84 – 1,275.79

7054 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,263.13 rating

Confidence interval: 1,256.02 – 1,270.24

8042 votes

Category
instruction_following
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,207.97 rating

Confidence interval: 1,186.03 – 1,229.91

809 votes

Category
japanese
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,206.80 rating

Confidence interval: 1,182.85 – 1,230.75

714 votes

Category
korean
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,298.50 rating

Confidence interval: 1,290.73 – 1,306.28

6342 votes

Category
longer_query
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,260.84 rating

Confidence interval: 1,247.76 – 1,273.93

2104 votes

Category
math
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,270.23 rating

Confidence interval: 1,261.61 – 1,278.85

5412 votes

Category
multi_turn
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,254.44 rating

Confidence interval: 1,248.92 – 1,259.96

18454 votes

Category
non_english
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,277.06 rating

Confidence interval: 1,272.53 – 1,281.59

32710 votes

Category
overall
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,241.51 rating

Confidence interval: 1,229.04 – 1,253.98

2794 votes

Category
polish
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,263.10 rating

Confidence interval: 1,251.27 – 1,274.94

2413 votes

Category
russian
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating

Mistral Small 3.1 24B Instruct (2503)

1,283.30 rating

Confidence interval: 1,261.52 – 1,305.09

810 votes

Category
spanish
Evaluated configuration
Mistral Small 3.1 24B Instruct (2503)
Evaluation type
human preference

Run it locally

Inference · memory estimate

Mistral Small 3.1 24B Instruct (2503)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0