Le barre mostrano i risultati delle prove. I segmenti indicano intervalli approssimativi al 95% quando è disponibile l’errore standard. Budget di ragionamento diversi non implicano costi uguali. I risultati mancanti non valgono zero.
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
GLM-4.7
1.494,73 rating
Intervallo di confidenza: 1.476,52 – 1.512,95
1020 voti
Categoria
chinese
Configurazione valutata
GLM-4.7
Tipo di valutazione
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
GLM-4.7
1.454,18 rating
Intervallo di confidenza: 1.442,44 – 1.465,92
2478 voti
Categoria
coding
Configurazione valutata
GLM-4.7
Tipo di valutazione
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
GLM-4.7
1.401,28 rating
Intervallo di confidenza: 1.388,18 – 1.414,39
1960 voti
Categoria
creative_writing
Configurazione valutata
GLM-4.7
Tipo di valutazione
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
GLM-4.7
1.453,03 rating
Intervallo di confidenza: 1.444,40 – 1.461,66
5027 voti
Categoria
english
Configurazione valutata
GLM-4.7
Tipo di valutazione
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
GLM-4.7
1.430,97 rating
Intervallo di confidenza: 1.422,58 – 1.439,36
8492 voti
Categoria
exclude_ties
Configurazione valutata
GLM-4.7
Tipo di valutazione
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
GLM-4.7
1.423,60 rating
Intervallo di confidenza: 1.403,16 – 1.444,03
807 voti
Categoria
expert
Configurazione valutata
GLM-4.7
Tipo di valutazione
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
GLM-4.7
1.431,96 rating
Intervallo di confidenza: 1.398,43 – 1.465,49
306 voti
Categoria
french
Configurazione valutata
GLM-4.7
Tipo di valutazione
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
GLM-4.7
1.426,16 rating
Intervallo di confidenza: 1.388,82 – 1.463,50
223 voti
Categoria
german
Configurazione valutata
GLM-4.7
Tipo di valutazione
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
GLM-4.7
1.442,97 rating
Intervallo di confidenza: 1.435,29 – 1.450,66
6788 voti
Categoria
hard_prompts
Configurazione valutata
GLM-4.7
Tipo di valutazione
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
GLM-4.7
1.452,45 rating
Intervallo di confidenza: 1.441,16 – 1.463,73
2699 voti
Categoria
hard_prompts_english
Configurazione valutata
GLM-4.7
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
GLM-4.7
1.401,03 rating
Intervallo di confidenza: 1.389,32 – 1.412,74
2426 voti
Categoria
industry_entertainment_and_sports_and_media
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
GLM-4.7
1.444,78 rating
Intervallo di confidenza: 1.426,25 – 1.463,30
970 voti
Categoria
industry_legal_and_government
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
GLM-4.7
1.457,86 rating
Intervallo di confidenza: 1.445,32 – 1.470,39
2142 voti
Categoria
industry_life_and_physical_and_social_science
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
GLM-4.7
1.411,48 rating
Intervallo di confidenza: 1.389,21 – 1.433,76
625 voti
Categoria
industry_mathematical
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
GLM-4.7
1.468,71 rating
Intervallo di confidenza: 1.448,66 – 1.488,76
826 voti
Categoria
industry_medicine_and_healthcare
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
GLM-4.7
1.453,51 rating
Intervallo di confidenza: 1.444,23 – 1.462,80
4126 voti
Categoria
industry_software_and_it_services
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
GLM-4.7
1.410,74 rating
Intervallo di confidenza: 1.399,76 – 1.421,72
2827 voti
Categoria
industry_writing_and_literature_and_language
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
GLM-4.7
1.412,05 rating
Intervallo di confidenza: 1.401,78 – 1.422,32
3306 voti
Categoria
instruction_following
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
GLM-4.7
1.438,72 rating
Intervallo di confidenza: 1.384,44 – 1.493,00
125 voti
Categoria
japanese
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
GLM-4.7
1.398,97 rating
Intervallo di confidenza: 1.355,85 – 1.442,08
177 voti
Categoria
korean
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
GLM-4.7
1.432,61 rating
Intervallo di confidenza: 1.422,28 – 1.442,93
3267 voti
Categoria
longer_query
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
GLM-4.7
1.423,95 rating
Intervallo di confidenza: 1.403,55 – 1.444,35
739 voti
Categoria
math
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
GLM-4.7
1.445,93 rating
Intervallo di confidenza: 1.432,53 – 1.459,34
1931 voti
Categoria
multi_turn
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
GLM-4.7
1.417,04 rating
Intervallo di confidenza: 1.409,63 – 1.424,46
7226 voti
Categoria
non_english
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
GLM-4.7
1.435,40 rating
Intervallo di confidenza: 1.429,39 – 1.441,42
12253 voti
Categoria
overall
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
GLM-4.7
1.434,97 rating
Intervallo di confidenza: 1.409,37 – 1.460,56
461 voti
Categoria
polish
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
GLM-4.7
1.422,90 rating
Intervallo di confidenza: 1.409,14 – 1.436,65
1645 voti
Categoria
russian
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
GLM-4.7
1.434,27 rating
Intervallo di confidenza: 1.403,47 – 1.465,07
345 voti
Categoria
spanish
Configurazione valutata
glm-4.7
Tipo di valutazione
human preference
Esecuzione locale
Inferenza · stima della memoria
GLM-4.7
667,5 GiB di payload dei tensori del checkpoint · 358,34 B elementi dei tensori archiviati · BF16/F32
I tensori archiviati possono includere buffer e copie di pesi condivisi. Il numero di parametri unici non è verificato. Le dimensioni del checkpoint non indicano la memoria necessaria per eseguire il modello.
Capacità
Finestra di contesto
202.752 tokens
Input massimo
Valore riportato 1: 203.000 tokens*
Valore riportato 2: 200.000 tokens*
Output massimo
128.000 tokens*
Ragionamento
Sì*
Uso di strumenti
Sì*
Output strutturato
Sì*
Pesi aperti
Sì
Modalità API
Chat*
Input immagini
No*
Input audio
No*
Cache dei prompt
Sì*
Messaggi di sistema
Sì*
Scelta degli strumenti
Sì*
Licenza del modello
mit
Payload dei tensori del checkpoint
667,46 GiB
Modalità di input
text
Modalità di output
text
Elaborazione e piattaforma
Architettura
glm4_moe
Configurazione di sistema
Specifiche dettagliate
Specifiche · 33 campi
cache creation input token cost
0*Ambito e condizioni
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
1,1e-7*Ambito e condizioni
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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.*
deprecation date
2027-03-30*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
6,0e-7*Ambito e condizioni
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
6,0e-7*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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 batches
3,0e-7*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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 flex
3,0e-7*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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 priority
1,05e-6*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
zai*Ambito e condizioni
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
bedrock_converse*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
203.000*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
200.000*Ambito e condizioni
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
128.000*Ambito e condizioni
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
128.000*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
128.000*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
2,2e-6*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
2,2e-6*Ambito e condizioni
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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 batches
1,1e-6*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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 flex
1,1e-6*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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 priority
3,85e-6*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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 audio input
No*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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 prompt caching
Sì*Ambito e condizioni
native_context
provider
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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 system messages
Sì*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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
zai*
mode
chat*
full_native_model_id
zai/glm-4.7*
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
No*Ambito e condizioni
native_context
provider
bedrock_converse*
mode
chat*
full_native_model_id
zai.glm-4.7*
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.*