GLM-5.3 (Max)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsGLM-5.3 (Max)
Model evaluation
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-5.3 (Max)
1,531.84 rating
Confidence interval: 1,518.19 – 1,545.49
2058 votes
- Category
- chinese
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,496.89 rating
Confidence interval: 1,488.77 – 1,505.02
6323 votes
- Category
- coding
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,459.44 rating
Confidence interval: 1,450.76 – 1,468.12
6017 votes
- Category
- creative_writing
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,482.63 rating
Confidence interval: 1,475.97 – 1,489.29
10670 votes
- Category
- english
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,479.52 rating
Confidence interval: 1,473.10 – 1,485.94
19610 votes
- Category
- exclude_ties
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,517.19 rating
Confidence interval: 1,505.17 – 1,529.21
2588 votes
- Category
- expert
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,495.72 rating
Confidence interval: 1,475.06 – 1,516.38
920 votes
- Category
- french
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,491.15 rating
Confidence interval: 1,462.72 – 1,519.59
413 votes
- Category
- german
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,490.29 rating
Confidence interval: 1,484.49 – 1,496.08
16697 votes
- Category
- hard_prompts
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,496.81 rating
Confidence interval: 1,488.88 – 1,504.73
6734 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,460.72 rating
Confidence interval: 1,451.66 – 1,469.77
4834 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,447.86 rating
Confidence interval: 1,439.77 – 1,455.95
7008 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,473.26 rating
Confidence interval: 1,460.30 – 1,486.21
2277 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,498.08 rating
Confidence interval: 1,488.75 – 1,507.41
4477 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,500.76 rating
Confidence interval: 1,485.06 – 1,516.46
1436 votes
- Category
- industry_mathematical
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,482.67 rating
Confidence interval: 1,468.64 – 1,496.70
1957 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,493.62 rating
Confidence interval: 1,486.73 – 1,500.50
9675 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,470.05 rating
Confidence interval: 1,462.28 – 1,477.82
7597 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,481.26 rating
Confidence interval: 1,474.04 – 1,488.49
8831 votes
- Category
- instruction_following
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,457.67 rating
Confidence interval: 1,429.78 – 1,485.57
489 votes
- Category
- japanese
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,457.12 rating
Confidence interval: 1,429.25 – 1,484.99
458 votes
- Category
- korean
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,483.46 rating
Confidence interval: 1,476.80 – 1,490.12
11977 votes
- Category
- longer_query
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,497.23 rating
Confidence interval: 1,480.19 – 1,514.27
1158 votes
- Category
- math
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,470.01 rating
Confidence interval: 1,459.98 – 1,480.04
3952 votes
- Category
- multi_turn
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,459.64 rating
Confidence interval: 1,453.85 – 1,465.43
15931 votes
- Category
- non_english
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,473.78 rating
Confidence interval: 1,468.85 – 1,478.70
26606 votes
- Category
- overall
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,461.64 rating
Confidence interval: 1,432.22 – 1,491.07
393 votes
- Category
- polish
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,470.93 rating
Confidence interval: 1,460.41 – 1,481.45
3432 votes
- Category
- russian
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
GLM-5.3 (Max)
1,466.13 rating
Confidence interval: 1,446.17 – 1,486.09
856 votes
- Category
- spanish
- Evaluated configuration
- GLM-5.3 (Max)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0