Preferenze complessive sul testo da confronti diretti. Non misura accuratezza fattuale o riuscita dei compiti.
14001440
Mistral Medium 3.5
Mistral Medium 3.5 · Intervallo 95% 1414,4–1427,1 · 11,791 voti · 2026-10-28
Risultati registrati
Ogni riga usa lo stesso benchmark, versione, carico, scenario e unità. I risultati mancanti non valgono zero. I risultati di sistema includono tutta la configurazione hardware e software.
Arena text preference / chinesehuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.445,45 rating
Intervallo di confidenza: 1.421,92 – 1.468,98
613 voti
Categoria
chinese
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.460,09 rating
Intervallo di confidenza: 1.449,40 – 1.470,78
3296 voti
Categoria
coding
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.373,81 rating
Intervallo di confidenza: 1.360,16 – 1.387,46
2070 voti
Categoria
creative_writing
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.432,87 rating
Intervallo di confidenza: 1.424,45 – 1.441,29
5671 voti
Categoria
english
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.410,08 rating
Intervallo di confidenza: 1.401,82 – 1.418,34
8933 voti
Categoria
exclude_ties
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.431,51 rating
Intervallo di confidenza: 1.414,62 – 1.448,41
1210 voti
Categoria
expert
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.448,87 rating
Intervallo di confidenza: 1.419,03 – 1.478,70
449 voti
Categoria
french
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.453,31 rating
Intervallo di confidenza: 1.409,82 – 1.496,81
174 voti
Categoria
german
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.436,51 rating
Intervallo di confidenza: 1.428,87 – 1.444,16
7650 voti
Categoria
hard_prompts
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
Mistral Medium 3.5
1.445,17 rating
Intervallo di confidenza: 1.435,16 – 1.455,17
3862 voti
Categoria
hard_prompts_english
Configurazione valutata
Mistral Medium 3.5
Tipo di valutazione
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.382,14 rating
Intervallo di confidenza: 1.370,16 – 1.394,11
2681 voti
Categoria
industry_entertainment_and_sports_and_media
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.437,99 rating
Intervallo di confidenza: 1.417,80 – 1.458,17
890 voti
Categoria
industry_legal_and_government
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.428,37 rating
Intervallo di confidenza: 1.414,73 – 1.442,00
1940 voti
Categoria
industry_life_and_physical_and_social_science
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.440,58 rating
Intervallo di confidenza: 1.417,75 – 1.463,40
652 voti
Categoria
industry_mathematical
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.408,34 rating
Intervallo di confidenza: 1.387,57 – 1.429,12
845 voti
Categoria
industry_medicine_and_healthcare
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.458,39 rating
Intervallo di confidenza: 1.449,23 – 1.467,56
4593 voti
Categoria
industry_software_and_it_services
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.384,37 rating
Intervallo di confidenza: 1.373,13 – 1.395,61
2988 voti
Categoria
industry_writing_and_literature_and_language
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.415,21 rating
Intervallo di confidenza: 1.405,27 – 1.425,15
3831 voti
Categoria
instruction_following
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.384,39 rating
Intervallo di confidenza: 1.340,89 – 1.427,89
189 voti
Categoria
korean
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.415,58 rating
Intervallo di confidenza: 1.406,58 – 1.424,59
5095 voti
Categoria
longer_query
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.431,17 rating
Intervallo di confidenza: 1.406,85 – 1.455,49
565 voti
Categoria
math
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.424,16 rating
Intervallo di confidenza: 1.410,23 – 1.438,09
1917 voti
Categoria
multi_turn
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.404,66 rating
Intervallo di confidenza: 1.396,54 – 1.412,78
6127 voti
Categoria
non_english
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.420,97 rating
Intervallo di confidenza: 1.414,59 – 1.427,34
11778 voti
Categoria
overall
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.429,70 rating
Intervallo di confidenza: 1.392,62 – 1.466,79
233 voti
Categoria
polish
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.394,75 rating
Intervallo di confidenza: 1.377,65 – 1.411,85
1235 voti
Categoria
russian
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
Mistral Medium 3.5
1.410,77 rating
Intervallo di confidenza: 1.379,72 – 1.441,81
389 voti
Categoria
spanish
Configurazione valutata
mistral-medium-3.5
Tipo di valutazione
human preference
Esecuzione locale
Inferenza · stima della memoria
Mistral Medium 3.5
Pesi chiusi. Non sono pubblicati un impiego locale supportato o requisiti GPU.
Costo API
USD / mese
Stima per token di testo standard. Esclude imposte, cache, sconti batch e costi aggiuntivi per ragionamento e modalità multimediali. Limiti e disponibilità possono variare per provider.
Mistral Medium 3.5
Capacità
Finestra di contesto
262.144 tokens
Input massimo
262.144 tokens*
Output massimo
209.715 tokens
Ragionamento
Sì
Uso di strumenti
Sì
Output strutturato
Sì*
Pesi aperti
No
Modalità API
Chat*
Input immagini
Sì*
Scelta degli strumenti
Sì*
Licenza del modello
Modified MIT
Modalità di input
text
image
pdf
Modalità di output
text
Configurazione di sistema
Specifiche dettagliate
Specifiche · 30 campi
cache read input token cost
1,5e-7*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
cache read input token cost
1,5e-7*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token
1,5e-6*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
input cost per token
1,5e-6*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
mistral*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
litellm provider
mistral*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max input tokens
262.144*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max input tokens
262.144*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max output tokens
262.144*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max output tokens
262.144*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max tokens
262.144*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
max tokens
262.144*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
chat*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
mode
chat*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token
7,5e-6*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
output cost per token
7,5e-6*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
reasoning effort levels
none*
high*
Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
reasoning effort levels
none*
high*
Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports assistant prefill
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports assistant prefill
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports function calling
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports function calling
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports reasoning
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports reasoning
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports response schema
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports response schema
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports tool choice
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports tool choice
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports vision
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3.5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*
supports vision
Sì*Ambito e condizioni
native_context
provider
mistral*
mode
chat*
full_native_model_id
mistral/mistral-medium-3-5*
pricing_scope
Literal source field names and values retained; provider, region, cache/batch/threshold conditions and per-unit meaning must be checked. max_tokens is not automatically a context limit.*