GeekRadar / The comparison desk
COMPARE.
AI models
zai

GLM-4-Plus (0111)

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

GLM-4-Plus (0111) 1330.8 GLM-4-Plus (0111) · 95% interval 1322.4–1339.2 · 5,760 votes · 2026-10-28

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-Plus (0111)

1,388.90 rating

Confidence interval: 1,359.18 – 1,418.61

387 votes

Category
chinese
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,286.37 rating

Confidence interval: 1,268.38 – 1,304.37

894 votes

Category
coding
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,310.56 rating

Confidence interval: 1,291.54 – 1,329.57

918 votes

Category
creative_writing
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,340.29 rating

Confidence interval: 1,330.02 – 1,350.56

3466 votes

Category
english
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,283.63 rating

Confidence interval: 1,271.12 – 1,296.14

3826 votes

Category
exclude_ties
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,279.07 rating

Confidence interval: 1,249.79 – 1,308.36

354 votes

Category
expert
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,340.97 rating

Confidence interval: 1,301.57 – 1,380.37

207 votes

Category
german
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,293.43 rating

Confidence interval: 1,279.19 – 1,307.68

1468 votes

Category
hard_prompts
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,291.52 rating

Confidence interval: 1,274.03 – 1,309.01

955 votes

Category
hard_prompts_english
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,326.45 rating

Confidence interval: 1,303.01 – 1,349.90

592 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,291.09 rating

Confidence interval: 1,273.84 – 1,308.35

1062 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,362.29 rating

Confidence interval: 1,332.31 – 1,392.27

367 votes

Category
industry_legal_and_government
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,350.33 rating

Confidence interval: 1,331.93 – 1,368.72

986 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,290.83 rating

Confidence interval: 1,270.01 – 1,311.64

638 votes

Category
industry_mathematical
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,389.98 rating

Confidence interval: 1,356.11 – 1,423.84

293 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,319.57 rating

Confidence interval: 1,304.82 – 1,334.32

1406 votes

Category
industry_software_and_it_services
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,326.28 rating

Confidence interval: 1,311.21 – 1,341.35

1459 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,292.37 rating

Confidence interval: 1,279.96 – 1,304.78

2160 votes

Category
instruction_following
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,225.35 rating

Confidence interval: 1,187.34 – 1,263.37

201 votes

Category
japanese
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,315.49 rating

Confidence interval: 1,295.32 – 1,335.66

765 votes

Category
longer_query
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,287.35 rating

Confidence interval: 1,268.12 – 1,306.58

721 votes

Category
math
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,323.68 rating

Confidence interval: 1,304.34 – 1,343.03

851 votes

Category
multi_turn
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,313.69 rating

Confidence interval: 1,301.58 – 1,325.80

2294 votes

Category
non_english
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,330.80 rating

Confidence interval: 1,322.42 – 1,339.19

5760 votes

Category
overall
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

GLM-4-Plus (0111)

1,312.48 rating

Confidence interval: 1,291.02 – 1,333.95

653 votes

Category
russian
Evaluated configuration
GLM-4-Plus (0111)
Evaluation type
human preference

Run it locally

Inference · memory estimate

GLM-4-Plus (0111)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary