GLM-4.5V
Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.
GeekRadar / The comparison desk
COMPARE.
AI modelsGLM-4.5V
AI model
- API mode
- Chat*
- Context window
- 65,536 tokens
- Maximum output
- 32,000 tokens*
- Open weights
- Yes
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
GLM-4.5V
1,336.88 rating
Confidence interval: 1,300.42 – 1,373.35
235 votes
- Category
- chinese
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
GLM-4.5V
1,347.35 rating
Confidence interval: 1,328.71 – 1,366.00
964 votes
- Category
- coding
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
GLM-4.5V
1,294.50 rating
Confidence interval: 1,271.74 – 1,317.26
613 votes
- Category
- creative_writing
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
GLM-4.5V
1,362.16 rating
Confidence interval: 1,349.48 – 1,374.83
2023 votes
- Category
- english
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
GLM-4.5V
1,282.28 rating
Confidence interval: 1,270.01 – 1,294.55
3363 votes
- Category
- exclude_ties
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
GLM-4.5V
1,352.61 rating
Confidence interval: 1,311.41 – 1,393.80
190 votes
- Category
- expert
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
GLM-4.5V
1,334.33 rating
Confidence interval: 1,322.31 – 1,346.34
2346 votes
- Category
- hard_prompts
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
GLM-4.5V
1,356.89 rating
Confidence interval: 1,338.86 – 1,374.91
1009 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
GLM-4.5V
1,308.96 rating
Confidence interval: 1,289.83 – 1,328.10
906 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
GLM-4.5V
1,303.07 rating
Confidence interval: 1,284.19 – 1,321.95
864 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
GLM-4.5V
1,337.88 rating
Confidence interval: 1,304.12 – 1,371.63
271 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
GLM-4.5V
1,329.72 rating
Confidence interval: 1,308.24 – 1,351.20
734 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
GLM-4.5V
1,335.54 rating
Confidence interval: 1,298.09 – 1,373.00
226 votes
- Category
- industry_mathematical
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
GLM-4.5V
1,349.04 rating
Confidence interval: 1,312.32 – 1,385.76
233 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
GLM-4.5V
1,352.42 rating
Confidence interval: 1,338.39 – 1,366.46
1693 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
GLM-4.5V
1,301.94 rating
Confidence interval: 1,284.36 – 1,319.51
1070 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
GLM-4.5V
1,310.45 rating
Confidence interval: 1,294.64 – 1,326.26
1292 votes
- Category
- instruction_following
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
GLM-4.5V
1,304.55 rating
Confidence interval: 1,286.75 – 1,322.34
1063 votes
- Category
- longer_query
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
GLM-4.5V
1,353.61 rating
Confidence interval: 1,319.42 – 1,387.81
269 votes
- Category
- math
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
GLM-4.5V
1,332.82 rating
Confidence interval: 1,312.58 – 1,353.06
850 votes
- Category
- multi_turn
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
GLM-4.5V
1,303.16 rating
Confidence interval: 1,292.15 – 1,314.17
2792 votes
- Category
- non_english
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
GLM-4.5V
1,332.63 rating
Confidence interval: 1,324.21 – 1,341.06
4817 votes
- Category
- overall
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
GLM-4.5V
1,302.34 rating
Confidence interval: 1,268.21 – 1,336.48
281 votes
- Category
- polish
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
GLM-4.5V
1,297.65 rating
Confidence interval: 1,270.23 – 1,325.08
394 votes
- Category
- russian
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
GLM-4.5V
1,335.58 rating
Confidence interval: 1,290.71 – 1,380.45
186 votes
- Category
- spanish
- Evaluated configuration
- GLM-4.5V
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
GLM-4.5V
1,337.01 rating
Confidence interval: 1,300.53 – 1,373.49
235 votes
- Category
- chinese
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
GLM-4.5V
1,347.54 rating
Confidence interval: 1,328.91 – 1,366.17
965 votes
- Category
- coding
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
GLM-4.5V
1,294.54 rating
Confidence interval: 1,271.81 – 1,317.27
614 votes
- Category
- creative_writing
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
GLM-4.5V
1,362.32 rating
Confidence interval: 1,349.66 – 1,374.98
2025 votes
- Category
- english
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
GLM-4.5V
1,282.31 rating
Confidence interval: 1,270.04 – 1,294.58
3363 votes
- Category
- exclude_ties
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
GLM-4.5V
1,352.68 rating
Confidence interval: 1,311.46 – 1,393.90
190 votes
- Category
- expert
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
GLM-4.5V
1,334.49 rating
Confidence interval: 1,322.48 – 1,346.50
2346 votes
- Category
- hard_prompts
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
GLM-4.5V
1,357.13 rating
Confidence interval: 1,339.12 – 1,375.15
1009 votes
- Category
- hard_prompts_english
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
GLM-4.5V
1,309.06 rating
Confidence interval: 1,289.92 – 1,328.19
906 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
GLM-4.5V
1,303.05 rating
Confidence interval: 1,284.19 – 1,321.91
865 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
GLM-4.5V
1,337.67 rating
Confidence interval: 1,303.90 – 1,371.44
271 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
GLM-4.5V
1,330.18 rating
Confidence interval: 1,308.75 – 1,351.61
735 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
GLM-4.5V
1,335.57 rating
Confidence interval: 1,298.10 – 1,373.04
226 votes
- Category
- industry_mathematical
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
GLM-4.5V
1,349.15 rating
Confidence interval: 1,312.42 – 1,385.89
233 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
GLM-4.5V
1,352.56 rating
Confidence interval: 1,338.53 – 1,366.59
1694 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
GLM-4.5V
1,301.98 rating
Confidence interval: 1,284.42 – 1,319.54
1071 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
GLM-4.5V
1,310.47 rating
Confidence interval: 1,294.69 – 1,326.26
1294 votes
- Category
- instruction_following
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
GLM-4.5V
1,304.65 rating
Confidence interval: 1,286.85 – 1,322.45
1063 votes
- Category
- longer_query
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
GLM-4.5V
1,353.65 rating
Confidence interval: 1,319.45 – 1,387.86
269 votes
- Category
- math
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
GLM-4.5V
1,333.15 rating
Confidence interval: 1,312.91 – 1,353.40
849 votes
- Category
- multi_turn
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
GLM-4.5V
1,303.15 rating
Confidence interval: 1,292.14 – 1,314.15
2794 votes
- Category
- non_english
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
GLM-4.5V
1,332.65 rating
Confidence interval: 1,324.23 – 1,341.07
4821 votes
- Category
- overall
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
GLM-4.5V
1,302.38 rating
Confidence interval: 1,268.24 – 1,336.51
281 votes
- Category
- polish
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
GLM-4.5V
1,297.71 rating
Confidence interval: 1,270.35 – 1,325.07
395 votes
- Category
- russian
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
GLM-4.5V
1,335.53 rating
Confidence interval: 1,290.65 – 1,380.42
186 votes
- Category
- spanish
- Evaluated configuration
- glm-4.5v
- Evaluation type
- human preference
Run it locally
Capabilities
- Context window
- 65,536 tokens
- Maximum input
- 128,000 tokens*
- Maximum output
- 32,000 tokens*
- Tool calling
- Yes*
- Open weights
- Yes
- API mode
- Chat*
- Image input
- Yes*
- Tool choice
- Yes*
- Model license
- mit
- Checkpoint tensor payload
- 200.63 GiB
Input modalities
- text
- image
Output modalities
- text
Processing & platform
- Architecture
- glm4v_moe
System configuration
Detailed specifications
Specifications · 9 fields
- input cost per token
- 6.0e-7*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.5v*
- 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*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.5v*
- 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
- 128,000*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.5v*
- 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
- 32,000*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.5v*
- 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*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.5v*
- 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
- 1.8e-6*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.5v*
- 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
- Yes*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.5v*
- 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
- Yes*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.5v*
- 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
- Yes*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.5v*
- 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.*
0 selected Compare 0
* Provisional data