GeekRadar / The comparison desk
COMPARE.
AI models
mistral

mistral-large-2402

Model evaluation

Capability & preference

Human preference · Arena

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

mistral-large-2402 1176.4 mistral-large-2402 · 95% interval 1171.8–1181.1 · 62,436 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-large-2402

1,120.29 rating

Confidence interval: 1,109.60 – 1,130.97

7840 votes

Category
chinese
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

mistral-large-2402

1,182.75 rating

Confidence interval: 1,174.29 – 1,191.22

10418 votes

Category
coding
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

mistral-large-2402

1,160.93 rating

Confidence interval: 1,151.58 – 1,170.28

9056 votes

Category
creative_writing
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

mistral-large-2402

1,199.84 rating

Confidence interval: 1,194.04 – 1,205.63

36796 votes

Category
english
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

mistral-large-2402

1,046.67 rating

Confidence interval: 1,039.80 – 1,053.54

41750 votes

Category
exclude_ties
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

mistral-large-2402

1,122.92 rating

Confidence interval: 1,109.31 – 1,136.53

2940 votes

Category
expert
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

mistral-large-2402

1,209.75 rating

Confidence interval: 1,185.85 – 1,233.65

1049 votes

Category
french
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

mistral-large-2402

1,177.91 rating

Confidence interval: 1,160.65 – 1,195.16

1690 votes

Category
german
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

mistral-large-2402

1,166.97 rating

Confidence interval: 1,160.06 – 1,173.89

17187 votes

Category
hard_prompts
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

mistral-large-2402

1,178.05 rating

Confidence interval: 1,169.80 – 1,186.31

11296 votes

Category
hard_prompts_english
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

mistral-large-2402

1,130.18 rating

Confidence interval: 1,120.00 – 1,140.36

6461 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

mistral-large-2402

1,150.71 rating

Confidence interval: 1,141.79 – 1,159.63

9175 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

mistral-large-2402

1,180.64 rating

Confidence interval: 1,167.15 – 1,194.13

3306 votes

Category
industry_legal_and_government
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

mistral-large-2402

1,153.76 rating

Confidence interval: 1,144.78 – 1,162.75

10875 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

mistral-large-2402

1,189.83 rating

Confidence interval: 1,180.35 – 1,199.32

7028 votes

Category
industry_mathematical
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

mistral-large-2402

1,133.18 rating

Confidence interval: 1,119.61 – 1,146.75

3434 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

mistral-large-2402

1,170.62 rating

Confidence interval: 1,163.37 – 1,177.86

17516 votes

Category
industry_software_and_it_services
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

mistral-large-2402

1,179.75 rating

Confidence interval: 1,172.11 – 1,187.40

15192 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

mistral-large-2402

1,169.06 rating

Confidence interval: 1,162.49 – 1,175.64

21532 votes

Category
instruction_following
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

mistral-large-2402

1,008.13 rating

Confidence interval: 985.26 – 1,030.99

945 votes

Category
japanese
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

mistral-large-2402

1,017.11 rating

Confidence interval: 994.08 – 1,040.15

1090 votes

Category
korean
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

mistral-large-2402

1,172.89 rating

Confidence interval: 1,163.03 – 1,182.75

6217 votes

Category
longer_query
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

mistral-large-2402

1,199.78 rating

Confidence interval: 1,190.77 – 1,208.78

7987 votes

Category
math
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

mistral-large-2402

1,171.99 rating

Confidence interval: 1,162.82 – 1,181.16

9521 votes

Category
multi_turn
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

mistral-large-2402

1,142.12 rating

Confidence interval: 1,135.92 – 1,148.31

25640 votes

Category
non_english
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

mistral-large-2402

1,176.44 rating

Confidence interval: 1,171.76 – 1,181.12

62436 votes

Category
overall
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

mistral-large-2402

1,157.22 rating

Confidence interval: 1,099.56 – 1,214.89

170 votes

Category
polish
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

mistral-large-2402

1,179.48 rating

Confidence interval: 1,168.96 – 1,190.00

5462 votes

Category
russian
Evaluated configuration
mistral-large-2402
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

mistral-large-2402

1,194.59 rating

Confidence interval: 1,169.91 – 1,219.26

886 votes

Category
spanish
Evaluated configuration
mistral-large-2402
Evaluation type
human preference

Run it locally

Inference · memory estimate

mistral-large-2402

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary