chatglm-6b
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelschatglm-6b
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
chatglm-6b
1,077.31 rating
Confidence interval: 1,038.90 – 1,115.72
267 votes
- Category
- chinese
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
chatglm-6b
919.19 rating
Confidence interval: 893.07 – 945.30
551 votes
- Category
- coding
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
chatglm-6b
899.91 rating
Confidence interval: 876.05 – 923.77
771 votes
- Category
- creative_writing
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
chatglm-6b
938.14 rating
Confidence interval: 924.73 – 951.55
4055 votes
- Category
- english
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
chatglm-6b
661.58 rating
Confidence interval: 642.84 – 680.32
3347 votes
- Category
- exclude_ties
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
chatglm-6b
900.93 rating
Confidence interval: 880.06 – 921.81
848 votes
- Category
- hard_prompts
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
chatglm-6b
896.13 rating
Confidence interval: 873.23 – 919.03
732 votes
- Category
- hard_prompts_english
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
chatglm-6b
845.54 rating
Confidence interval: 808.26 – 882.82
300 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
chatglm-6b
840.92 rating
Confidence interval: 816.90 – 864.94
774 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
chatglm-6b
895.29 rating
Confidence interval: 848.77 – 941.81
195 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
chatglm-6b
849.37 rating
Confidence interval: 824.60 – 874.15
819 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
chatglm-6b
911.96 rating
Confidence interval: 884.51 – 939.40
466 votes
- Category
- industry_mathematical
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
chatglm-6b
823.99 rating
Confidence interval: 771.81 – 876.16
193 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
chatglm-6b
888.39 rating
Confidence interval: 868.77 – 908.01
1162 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
chatglm-6b
925.37 rating
Confidence interval: 905.44 – 945.29
1056 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
chatglm-6b
901.72 rating
Confidence interval: 884.28 – 919.15
1277 votes
- Category
- instruction_following
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
chatglm-6b
925.66 rating
Confidence interval: 900.49 – 950.84
525 votes
- Category
- math
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
chatglm-6b
856.42 rating
Confidence interval: 827.26 – 885.57
492 votes
- Category
- multi_turn
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
chatglm-6b
904.83 rating
Confidence interval: 883.45 – 926.21
859 votes
- Category
- non_english
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
chatglm-6b
918.42 rating
Confidence interval: 906.20 – 930.64
4914 votes
- Category
- overall
- Evaluated configuration
- chatglm-6b
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Non-commercial
0 selected Compare 0