GLM-5.2 (Max)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsGLM-5.2 (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-5.2 (Max)
1,523.40 rating
Confidence interval: 1,513.34 – 1,533.46
3876 votes
- Category
- chinese
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,486.82 rating
Confidence interval: 1,480.82 – 1,492.83
14324 votes
- Category
- coding
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,460.86 rating
Confidence interval: 1,454.04 – 1,467.69
10646 votes
- Category
- creative_writing
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,474.94 rating
Confidence interval: 1,469.78 – 1,480.09
21897 votes
- Category
- english
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,474.96 rating
Confidence interval: 1,469.75 – 1,480.16
39709 votes
- Category
- exclude_ties
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,488.47 rating
Confidence interval: 1,479.98 – 1,496.97
5595 votes
- Category
- expert
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,475.86 rating
Confidence interval: 1,461.14 – 1,490.59
2010 votes
- Category
- french
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,471.43 rating
Confidence interval: 1,451.67 – 1,491.18
966 votes
- Category
- german
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,480.56 rating
Confidence interval: 1,475.93 – 1,485.20
34803 votes
- Category
- hard_prompts
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,481.45 rating
Confidence interval: 1,475.48 – 1,487.42
14418 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,450.56 rating
Confidence interval: 1,443.92 – 1,457.20
10212 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,448.04 rating
Confidence interval: 1,441.74 – 1,454.34
13277 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,487.33 rating
Confidence interval: 1,477.72 – 1,496.94
4327 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,488.06 rating
Confidence interval: 1,481.09 – 1,495.02
8917 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,489.33 rating
Confidence interval: 1,477.96 – 1,500.69
2920 votes
- Category
- industry_mathematical
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,475.02 rating
Confidence interval: 1,464.94 – 1,485.10
3933 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,486.68 rating
Confidence interval: 1,481.40 – 1,491.97
20769 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,461.40 rating
Confidence interval: 1,455.35 – 1,467.45
14305 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,465.61 rating
Confidence interval: 1,460.10 – 1,471.11
18494 votes
- Category
- instruction_following
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,450.01 rating
Confidence interval: 1,428.19 – 1,471.82
887 votes
- Category
- japanese
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,438.10 rating
Confidence interval: 1,418.70 – 1,457.49
1037 votes
- Category
- korean
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,479.00 rating
Confidence interval: 1,473.77 – 1,484.24
24397 votes
- Category
- longer_query
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,483.71 rating
Confidence interval: 1,471.56 – 1,495.86
2423 votes
- Category
- math
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,469.05 rating
Confidence interval: 1,461.85 – 1,476.24
8490 votes
- Category
- multi_turn
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,458.23 rating
Confidence interval: 1,453.58 – 1,462.88
31793 votes
- Category
- non_english
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,469.64 rating
Confidence interval: 1,465.59 – 1,473.69
53702 votes
- Category
- overall
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,456.65 rating
Confidence interval: 1,436.31 – 1,476.99
869 votes
- Category
- polish
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,466.77 rating
Confidence interval: 1,458.79 – 1,474.75
6377 votes
- Category
- russian
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
GLM-5.2 (Max)
1,477.69 rating
Confidence interval: 1,462.34 – 1,493.03
1651 votes
- Category
- spanish
- Evaluated configuration
- GLM-5.2 (Max)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- MIT
0 selected Compare 0