GLM-4.6V
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-4.6V
AI model
- Context window
- 131,072 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-4.6V
1,424.58 rating
Confidence interval: 1,390.52 – 1,458.65
275 votes
- Category
- chinese
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
GLM-4.6V
1,389.76 rating
Confidence interval: 1,365.11 – 1,414.42
542 votes
- Category
- coding
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
GLM-4.6V
1,347.33 rating
Confidence interval: 1,319.30 – 1,375.36
425 votes
- Category
- creative_writing
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
GLM-4.6V
1,394.88 rating
Confidence interval: 1,377.95 – 1,411.80
1167 votes
- Category
- english
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
GLM-4.6V
1,347.39 rating
Confidence interval: 1,331.71 – 1,363.06
2017 votes
- Category
- exclude_ties
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
GLM-4.6V
1,372.59 rating
Confidence interval: 1,330.92 – 1,414.26
185 votes
- Category
- expert
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
GLM-4.6V
1,367.54 rating
Confidence interval: 1,352.68 – 1,382.40
1535 votes
- Category
- hard_prompts
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
GLM-4.6V
1,390.97 rating
Confidence interval: 1,368.09 – 1,413.85
641 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
GLM-4.6V
1,359.29 rating
Confidence interval: 1,334.67 – 1,383.91
552 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
GLM-4.6V
1,343.35 rating
Confidence interval: 1,317.90 – 1,368.80
520 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
GLM-4.6V
1,394.22 rating
Confidence interval: 1,354.24 – 1,434.19
212 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
GLM-4.6V
1,389.24 rating
Confidence interval: 1,363.01 – 1,415.48
482 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
GLM-4.6V
1,389.27 rating
Confidence interval: 1,347.92 – 1,430.61
188 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
GLM-4.6V
1,391.15 rating
Confidence interval: 1,372.18 – 1,410.13
934 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
GLM-4.6V
1,347.13 rating
Confidence interval: 1,323.88 – 1,370.37
623 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
GLM-4.6V
1,351.30 rating
Confidence interval: 1,330.19 – 1,372.41
754 votes
- Category
- instruction_following
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
GLM-4.6V
1,357.64 rating
Confidence interval: 1,335.62 – 1,379.67
704 votes
- Category
- longer_query
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
GLM-4.6V
1,358.90 rating
Confidence interval: 1,332.98 – 1,384.82
488 votes
- Category
- multi_turn
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
GLM-4.6V
1,358.79 rating
Confidence interval: 1,344.73 – 1,372.85
1666 votes
- Category
- non_english
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
GLM-4.6V
1,376.48 rating
Confidence interval: 1,365.34 – 1,387.62
2833 votes
- Category
- overall
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
GLM-4.6V
1,339.85 rating
Confidence interval: 1,310.17 – 1,369.52
356 votes
- Category
- russian
- Evaluated configuration
- GLM-4.6V
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
GLM-4.6V
1,424.75 rating
Confidence interval: 1,390.67 – 1,458.83
275 votes
- Category
- chinese
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
GLM-4.6V
1,389.47 rating
Confidence interval: 1,364.90 – 1,414.03
545 votes
- Category
- coding
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
GLM-4.6V
1,347.22 rating
Confidence interval: 1,319.11 – 1,375.33
424 votes
- Category
- creative_writing
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
GLM-4.6V
1,394.62 rating
Confidence interval: 1,377.71 – 1,411.54
1169 votes
- Category
- english
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
GLM-4.6V
1,347.12 rating
Confidence interval: 1,331.45 – 1,362.79
2019 votes
- Category
- exclude_ties
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
GLM-4.6V
1,372.54 rating
Confidence interval: 1,330.86 – 1,414.21
185 votes
- Category
- expert
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
GLM-4.6V
1,367.57 rating
Confidence interval: 1,352.72 – 1,382.42
1536 votes
- Category
- hard_prompts
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
GLM-4.6V
1,390.96 rating
Confidence interval: 1,368.11 – 1,413.82
642 votes
- Category
- hard_prompts_english
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
GLM-4.6V
1,359.47 rating
Confidence interval: 1,334.89 – 1,384.05
553 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
GLM-4.6V
1,343.50 rating
Confidence interval: 1,318.09 – 1,368.92
521 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
GLM-4.6V
1,394.11 rating
Confidence interval: 1,354.12 – 1,434.10
212 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
GLM-4.6V
1,389.21 rating
Confidence interval: 1,362.91 – 1,415.50
481 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
GLM-4.6V
1,389.26 rating
Confidence interval: 1,347.90 – 1,430.62
188 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
GLM-4.6V
1,390.87 rating
Confidence interval: 1,371.89 – 1,409.84
935 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
GLM-4.6V
1,346.65 rating
Confidence interval: 1,323.48 – 1,369.82
626 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
GLM-4.6V
1,350.95 rating
Confidence interval: 1,329.87 – 1,372.03
756 votes
- Category
- instruction_following
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
GLM-4.6V
1,357.27 rating
Confidence interval: 1,335.27 – 1,379.26
706 votes
- Category
- longer_query
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
GLM-4.6V
1,358.80 rating
Confidence interval: 1,332.87 – 1,384.73
488 votes
- Category
- multi_turn
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
GLM-4.6V
1,358.70 rating
Confidence interval: 1,344.64 – 1,372.75
1668 votes
- Category
- non_english
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
GLM-4.6V
1,376.37 rating
Confidence interval: 1,365.24 – 1,387.50
2837 votes
- Category
- overall
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
GLM-4.6V
1,339.08 rating
Confidence interval: 1,309.41 – 1,368.74
357 votes
- Category
- russian
- Evaluated configuration
- glm-4.6v
- Evaluation type
- human preference
Run it locally
Capabilities
- Context window
- 131,072 tokens
- Open weights
- Yes
- Model license
- mit
- Checkpoint tensor payload
- 200.63 GiB
Input modalities
- text
- image
Output modalities
- text
Processing & platform
- Architecture
- glm4v_moe
0 selected Compare 0