glm-4-plus
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsglm-4-plus
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 · 2026-10-15 · rating
glm-4-plus
1,295.86 rating
Confidence interval: 1,282.95 – 1,308.76
2427 votes
- Category
- chinese
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
glm-4-plus
1,290.27 rating
Confidence interval: 1,280.99 – 1,299.55
4449 votes
- Category
- coding
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
glm-4-plus
1,263.45 rating
Confidence interval: 1,253.25 – 1,273.66
3801 votes
- Category
- creative_writing
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
glm-4-plus
1,296.59 rating
Confidence interval: 1,290.20 – 1,302.97
13191 votes
- Category
- english
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
glm-4-plus
1,221.14 rating
Confidence interval: 1,213.51 – 1,228.77
16416 votes
- Category
- exclude_ties
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
glm-4-plus
1,251.67 rating
Confidence interval: 1,236.98 – 1,266.36
1608 votes
- Category
- expert
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
glm-4-plus
1,308.14 rating
Confidence interval: 1,271.58 – 1,344.69
286 votes
- Category
- french
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
glm-4-plus
1,278.48 rating
Confidence interval: 1,255.56 – 1,301.41
659 votes
- Category
- german
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
glm-4-plus
1,272.83 rating
Confidence interval: 1,265.16 – 1,280.51
7067 votes
- Category
- hard_prompts
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
glm-4-plus
1,279.45 rating
Confidence interval: 1,269.91 – 1,288.99
4016 votes
- Category
- hard_prompts_english
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
glm-4-plus
1,273.10 rating
Confidence interval: 1,261.95 – 1,284.25
3267 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
glm-4-plus
1,249.81 rating
Confidence interval: 1,239.80 – 1,259.82
3855 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
glm-4-plus
1,309.03 rating
Confidence interval: 1,293.89 – 1,324.17
1723 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
glm-4-plus
1,294.53 rating
Confidence interval: 1,284.94 – 1,304.13
4702 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
glm-4-plus
1,282.57 rating
Confidence interval: 1,271.96 – 1,293.18
2991 votes
- Category
- industry_mathematical
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
glm-4-plus
1,289.56 rating
Confidence interval: 1,273.92 – 1,305.20
1513 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
glm-4-plus
1,291.10 rating
Confidence interval: 1,283.15 – 1,299.05
7097 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
glm-4-plus
1,278.59 rating
Confidence interval: 1,270.32 – 1,286.86
7164 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
glm-4-plus
1,264.12 rating
Confidence interval: 1,257.25 – 1,270.99
10743 votes
- Category
- instruction_following
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
glm-4-plus
1,207.31 rating
Confidence interval: 1,180.00 – 1,234.61
485 votes
- Category
- japanese
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
glm-4-plus
1,243.53 rating
Confidence interval: 1,210.99 – 1,276.08
374 votes
- Category
- korean
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
glm-4-plus
1,285.71 rating
Confidence interval: 1,275.68 – 1,295.74
3992 votes
- Category
- longer_query
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
glm-4-plus
1,274.81 rating
Confidence interval: 1,264.86 – 1,284.76
3599 votes
- Category
- math
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
glm-4-plus
1,289.07 rating
Confidence interval: 1,279.61 – 1,298.52
4844 votes
- Category
- multi_turn
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
glm-4-plus
1,275.29 rating
Confidence interval: 1,268.74 – 1,281.84
12935 votes
- Category
- non_english
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
glm-4-plus
1,289.62 rating
Confidence interval: 1,284.72 – 1,294.51
26126 votes
- Category
- overall
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
glm-4-plus
1,275.14 rating
Confidence interval: 1,265.05 – 1,285.22
3904 votes
- Category
- russian
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
glm-4-plus
1,310.62 rating
Confidence interval: 1,278.51 – 1,342.74
332 votes
- Category
- spanish
- Evaluated configuration
- glm-4-plus
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Proprietary
0 selected Compare 0