Mistral Medium 3.1 (2508)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsMistral Medium 3.1 (2508)
Model evaluation
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
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 Medium 3.1 (2508)
1,447.05 rating
Confidence interval: 1,439.80 – 1,454.31
7164 votes
- Category
- chinese
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,433.18 rating
Confidence interval: 1,428.64 – 1,437.71
21537 votes
- Category
- coding
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,390.60 rating
Confidence interval: 1,385.14 – 1,396.06
14026 votes
- Category
- creative_writing
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,437.94 rating
Confidence interval: 1,434.38 – 1,441.50
40838 votes
- Category
- english
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,415.00 rating
Confidence interval: 1,411.41 – 1,418.58
68441 votes
- Category
- exclude_ties
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,408.54 rating
Confidence interval: 1,401.05 – 1,416.03
6570 votes
- Category
- expert
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,459.85 rating
Confidence interval: 1,445.97 – 1,473.72
2110 votes
- Category
- french
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,432.45 rating
Confidence interval: 1,417.85 – 1,447.05
1743 votes
- Category
- german
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,425.61 rating
Confidence interval: 1,422.32 – 1,428.90
52895 votes
- Category
- hard_prompts
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,434.77 rating
Confidence interval: 1,430.35 – 1,439.19
23166 votes
- Category
- hard_prompts_english
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,417.70 rating
Confidence interval: 1,412.81 – 1,422.59
17850 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,389.55 rating
Confidence interval: 1,384.67 – 1,394.43
18043 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,439.22 rating
Confidence interval: 1,431.78 – 1,446.65
6698 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,444.23 rating
Confidence interval: 1,439.05 – 1,449.42
15288 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,412.18 rating
Confidence interval: 1,403.78 – 1,420.58
5099 votes
- Category
- industry_mathematical
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,449.49 rating
Confidence interval: 1,441.50 – 1,457.48
5994 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,436.25 rating
Confidence interval: 1,432.45 – 1,440.05
33902 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,395.11 rating
Confidence interval: 1,390.60 – 1,399.62
21936 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,397.59 rating
Confidence interval: 1,393.48 – 1,401.70
27620 votes
- Category
- instruction_following
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,378.79 rating
Confidence interval: 1,360.86 – 1,396.73
1128 votes
- Category
- japanese
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,380.55 rating
Confidence interval: 1,366.55 – 1,394.56
2000 votes
- Category
- korean
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,405.61 rating
Confidence interval: 1,401.42 – 1,409.79
27777 votes
- Category
- longer_query
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,408.45 rating
Confidence interval: 1,400.78 – 1,416.13
5993 votes
- Category
- math
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,417.97 rating
Confidence interval: 1,412.88 – 1,423.06
16388 votes
- Category
- multi_turn
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,407.71 rating
Confidence interval: 1,404.50 – 1,410.91
54405 votes
- Category
- non_english
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,424.22 rating
Confidence interval: 1,421.65 – 1,426.78
95269 votes
- Category
- overall
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,429.82 rating
Confidence interval: 1,419.32 – 1,440.32
3327 votes
- Category
- polish
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,410.97 rating
Confidence interval: 1,404.76 – 1,417.17
9721 votes
- Category
- russian
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
Mistral Medium 3.1 (2508)
1,433.23 rating
Confidence interval: 1,421.40 – 1,445.06
2870 votes
- Category
- spanish
- Evaluated configuration
- Mistral Medium 3.1 (2508)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Proprietary
0 selected Compare 0