GeekRadar / The comparison desk
COMPARE.
AI models
mistral

Mistral 7B Instruct

Model evaluation

Capability & preference

Human preference · Arena

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

Mistral 7B Instruct 1023.5 Mistral 7B Instruct · 95% interval 1014.3–1032.6 · 8,977 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 7B Instruct

931.41 rating

Confidence interval: 898.60 – 964.22

274 votes

Category
chinese
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,018.15 rating

Confidence interval: 998.72 – 1,037.59

1032 votes

Category
coding
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,028.07 rating

Confidence interval: 1,011.21 – 1,044.93

1689 votes

Category
creative_writing
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,058.82 rating

Confidence interval: 1,048.71 – 1,068.92

7073 votes

Category
english
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

Mistral 7B Instruct

818.89 rating

Confidence interval: 805.41 – 832.37

5974 votes

Category
exclude_ties
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

Mistral 7B Instruct

953.73 rating

Confidence interval: 914.86 – 992.60

183 votes

Category
expert
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

945.89 rating

Confidence interval: 897.47 – 994.30

175 votes

Category
french
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

931.07 rating

Confidence interval: 885.59 – 976.55

174 votes

Category
german
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,001.44 rating

Confidence interval: 986.34 – 1,016.54

1917 votes

Category
hard_prompts
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,021.75 rating

Confidence interval: 1,005.41 – 1,038.09

1616 votes

Category
hard_prompts_english
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

Mistral 7B Instruct

952.36 rating

Confidence interval: 928.78 – 975.94

747 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

Mistral 7B Instruct

999.46 rating

Confidence interval: 982.11 – 1,016.80

1497 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,024.54 rating

Confidence interval: 995.26 – 1,053.81

487 votes

Category
industry_legal_and_government
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

Mistral 7B Instruct

998.41 rating

Confidence interval: 980.46 – 1,016.36

1577 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,009.19 rating

Confidence interval: 988.17 – 1,030.21

814 votes

Category
industry_mathematical
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

Mistral 7B Instruct

993.60 rating

Confidence interval: 966.14 – 1,021.05

477 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,014.50 rating

Confidence interval: 998.87 – 1,030.12

2096 votes

Category
industry_software_and_it_services
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,030.27 rating

Confidence interval: 1,015.24 – 1,045.31

2336 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,003.12 rating

Confidence interval: 989.63 – 1,016.61

2768 votes

Category
instruction_following
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,000.33 rating

Confidence interval: 973.83 – 1,026.83

448 votes

Category
longer_query
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,027.44 rating

Confidence interval: 1,008.70 – 1,046.18

974 votes

Category
math
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,008.09 rating

Confidence interval: 988.88 – 1,027.31

1259 votes

Category
multi_turn
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

943.52 rating

Confidence interval: 927.76 – 959.29

1904 votes

Category
non_english
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,023.48 rating

Confidence interval: 1,014.32 – 1,032.64

8977 votes

Category
overall
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

Mistral 7B Instruct

1,001.19 rating

Confidence interval: 960.52 – 1,041.86

175 votes

Category
russian
Evaluated configuration
Mistral 7B Instruct
Evaluation type
human preference

Run it locally

Inference · memory estimate

Mistral 7B Instruct

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Apache 2.0