GLM-4.6
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-4.6
AI model
- API mode
- Chat*
- Context window
- 202,752 tokens
- Maximum output
- 128,000 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-4.6
1,498.91 rating
Confidence interval: 1,487.51 – 1,510.30
2721 votes
- Category
- chinese
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
GLM-4.6
1,448.66 rating
Confidence interval: 1,441.53 – 1,455.80
7593 votes
- Category
- coding
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
GLM-4.6
1,411.86 rating
Confidence interval: 1,403.39 – 1,420.32
5146 votes
- Category
- creative_writing
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
GLM-4.6
1,448.87 rating
Confidence interval: 1,443.51 – 1,454.24
15319 votes
- Category
- english
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
GLM-4.6
1,437.13 rating
Confidence interval: 1,431.68 – 1,442.58
25098 votes
- Category
- exclude_ties
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
GLM-4.6
1,431.38 rating
Confidence interval: 1,418.47 – 1,444.28
2062 votes
- Category
- expert
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
GLM-4.6
1,459.60 rating
Confidence interval: 1,436.90 – 1,482.30
706 votes
- Category
- french
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
GLM-4.6
1,446.92 rating
Confidence interval: 1,424.71 – 1,469.13
681 votes
- Category
- german
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
GLM-4.6
1,440.30 rating
Confidence interval: 1,435.35 – 1,445.26
19440 votes
- Category
- hard_prompts
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
GLM-4.6
1,444.90 rating
Confidence interval: 1,438.00 – 1,451.80
8251 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
GLM-4.6
1,416.26 rating
Confidence interval: 1,408.76 – 1,423.77
6901 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
GLM-4.6
1,408.70 rating
Confidence interval: 1,401.29 – 1,416.11
6682 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
GLM-4.6
1,448.13 rating
Confidence interval: 1,436.34 – 1,459.91
2450 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
GLM-4.6
1,456.06 rating
Confidence interval: 1,448.20 – 1,463.92
5931 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
GLM-4.6
1,446.62 rating
Confidence interval: 1,432.91 – 1,460.32
1783 votes
- Category
- industry_mathematical
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
GLM-4.6
1,454.93 rating
Confidence interval: 1,441.50 – 1,468.35
1934 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
GLM-4.6
1,455.20 rating
Confidence interval: 1,449.38 – 1,461.01
12601 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
GLM-4.6
1,415.54 rating
Confidence interval: 1,408.61 – 1,422.47
8090 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
GLM-4.6
1,410.24 rating
Confidence interval: 1,403.96 – 1,416.53
10285 votes
- Category
- instruction_following
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
GLM-4.6
1,393.00 rating
Confidence interval: 1,363.08 – 1,422.91
373 votes
- Category
- japanese
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
GLM-4.6
1,401.70 rating
Confidence interval: 1,376.98 – 1,426.42
617 votes
- Category
- korean
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
GLM-4.6
1,422.43 rating
Confidence interval: 1,415.88 – 1,428.97
9136 votes
- Category
- longer_query
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
GLM-4.6
1,431.84 rating
Confidence interval: 1,419.30 – 1,444.38
2151 votes
- Category
- math
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
GLM-4.6
1,426.96 rating
Confidence interval: 1,418.81 – 1,435.11
5613 votes
- Category
- multi_turn
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
GLM-4.6
1,426.26 rating
Confidence interval: 1,421.44 – 1,431.07
20455 votes
- Category
- non_english
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
GLM-4.6
1,440.06 rating
Confidence interval: 1,436.17 – 1,443.94
35810 votes
- Category
- overall
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
GLM-4.6
1,447.09 rating
Confidence interval: 1,430.86 – 1,463.32
1300 votes
- Category
- polish
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
GLM-4.6
1,418.39 rating
Confidence interval: 1,408.82 – 1,427.97
3542 votes
- Category
- russian
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
GLM-4.6
1,436.45 rating
Confidence interval: 1,417.48 – 1,455.42
1016 votes
- Category
- spanish
- Evaluated configuration
- GLM-4.6
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
GLM-4.6
1,499.16 rating
Confidence interval: 1,487.77 – 1,510.56
2722 votes
- Category
- chinese
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
GLM-4.6
1,448.64 rating
Confidence interval: 1,441.51 – 1,455.77
7602 votes
- Category
- coding
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
GLM-4.6
1,411.62 rating
Confidence interval: 1,403.15 – 1,420.08
5145 votes
- Category
- creative_writing
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
GLM-4.6
1,448.83 rating
Confidence interval: 1,443.47 – 1,454.20
15323 votes
- Category
- english
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
GLM-4.6
1,436.99 rating
Confidence interval: 1,431.54 – 1,442.44
25102 votes
- Category
- exclude_ties
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
GLM-4.6
1,431.51 rating
Confidence interval: 1,418.61 – 1,444.42
2063 votes
- Category
- expert
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
GLM-4.6
1,459.21 rating
Confidence interval: 1,436.50 – 1,481.93
706 votes
- Category
- french
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
GLM-4.6
1,446.88 rating
Confidence interval: 1,424.66 – 1,469.10
681 votes
- Category
- german
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
GLM-4.6
1,440.15 rating
Confidence interval: 1,435.20 – 1,445.11
19455 votes
- Category
- hard_prompts
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
GLM-4.6
1,444.80 rating
Confidence interval: 1,437.90 – 1,451.70
8254 votes
- Category
- hard_prompts_english
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
GLM-4.6
1,416.22 rating
Confidence interval: 1,408.72 – 1,423.72
6902 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
GLM-4.6
1,408.55 rating
Confidence interval: 1,401.15 – 1,415.96
6679 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
GLM-4.6
1,447.99 rating
Confidence interval: 1,436.20 – 1,459.78
2450 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
GLM-4.6
1,456.24 rating
Confidence interval: 1,448.39 – 1,464.10
5930 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
GLM-4.6
1,446.66 rating
Confidence interval: 1,432.95 – 1,460.37
1783 votes
- Category
- industry_mathematical
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
GLM-4.6
1,455.00 rating
Confidence interval: 1,441.57 – 1,468.43
1934 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
GLM-4.6
1,455.26 rating
Confidence interval: 1,449.45 – 1,461.07
12610 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
GLM-4.6
1,415.41 rating
Confidence interval: 1,408.48 – 1,422.33
8091 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
GLM-4.6
1,410.09 rating
Confidence interval: 1,403.81 – 1,416.38
10293 votes
- Category
- instruction_following
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
GLM-4.6
1,392.84 rating
Confidence interval: 1,362.91 – 1,422.77
373 votes
- Category
- japanese
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
GLM-4.6
1,400.05 rating
Confidence interval: 1,375.32 – 1,424.79
617 votes
- Category
- korean
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
GLM-4.6
1,422.40 rating
Confidence interval: 1,415.85 – 1,428.94
9145 votes
- Category
- longer_query
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
GLM-4.6
1,431.96 rating
Confidence interval: 1,419.43 – 1,444.50
2153 votes
- Category
- math
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
GLM-4.6
1,426.97 rating
Confidence interval: 1,418.82 – 1,435.11
5615 votes
- Category
- multi_turn
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
GLM-4.6
1,426.15 rating
Confidence interval: 1,421.33 – 1,430.96
20465 votes
- Category
- non_english
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
GLM-4.6
1,439.92 rating
Confidence interval: 1,436.03 – 1,443.80
35824 votes
- Category
- overall
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
GLM-4.6
1,446.74 rating
Confidence interval: 1,430.51 – 1,462.97
1301 votes
- Category
- polish
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
GLM-4.6
1,418.56 rating
Confidence interval: 1,408.99 – 1,428.13
3546 votes
- Category
- russian
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
GLM-4.6
1,435.97 rating
Confidence interval: 1,416.99 – 1,454.96
1015 votes
- Category
- spanish
- Evaluated configuration
- glm-4.6
- Evaluation type
- human preference
Run it locally
Capabilities
- Context window
- 202,752 tokens
- Maximum input
- 200,000 tokens*
- Maximum output
- 128,000 tokens*
- Reasoning
- Yes*
- Tool calling
- Yes*
- Open weights
- Yes
- API mode
- Chat*
- Prompt caching
- Yes*
- Tool choice
- Yes*
- Model license
- mit
- Checkpoint tensor payload
- 664.57 GiB
Input modalities
- text
Output modalities
- text
Processing & platform
- Architecture
- glm4_moe
System configuration
Detailed specifications
Specifications · 12 fields
- cache creation input token cost
- 0*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.6*
- 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*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.6*
- 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*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.6*
- 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-4.6*
- 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*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.6*
- 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*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.6*
- 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-4.6*
- 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*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.6*
- 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-4.6*
- 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
- Yes*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.6*
- 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
- Yes*
Scope and conditions
- native_context
- provider
- zai*
- mode
- chat*
- full_native_model_id
- zai/glm-4.6*
- 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-4.6*
- 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