chatglm2-6b
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelschatglm2-6b
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 / codinghuman preference · 2026-10-15 · rating
chatglm2-6b
901.74 rating
Confidence interval: 867.55 – 935.92
293 votes
- Category
- coding
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
chatglm2-6b
940.99 rating
Confidence interval: 914.73 – 967.24
566 votes
- Category
- creative_writing
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
chatglm2-6b
973.36 rating
Confidence interval: 958.46 – 988.26
2059 votes
- Category
- english
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
chatglm2-6b
684.72 rating
Confidence interval: 663.24 – 706.20
1894 votes
- Category
- exclude_ties
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
chatglm2-6b
916.89 rating
Confidence interval: 890.80 – 942.99
490 votes
- Category
- hard_prompts
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
chatglm2-6b
938.71 rating
Confidence interval: 910.10 – 967.33
408 votes
- Category
- hard_prompts_english
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
chatglm2-6b
887.04 rating
Confidence interval: 845.95 – 928.14
234 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
chatglm2-6b
921.76 rating
Confidence interval: 893.77 – 949.75
483 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
chatglm2-6b
915.75 rating
Confidence interval: 885.53 – 945.98
436 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
chatglm2-6b
917.39 rating
Confidence interval: 892.97 – 941.81
653 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
chatglm2-6b
952.67 rating
Confidence interval: 930.17 – 975.17
775 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
chatglm2-6b
901.96 rating
Confidence interval: 879.66 – 924.26
762 votes
- Category
- instruction_following
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
chatglm2-6b
915.11 rating
Confidence interval: 880.69 – 949.52
227 votes
- Category
- math
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
chatglm2-6b
902.01 rating
Confidence interval: 869.70 – 934.31
369 votes
- Category
- multi_turn
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
chatglm2-6b
857.25 rating
Confidence interval: 832.29 – 882.21
599 votes
- Category
- non_english
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
chatglm2-6b
938.58 rating
Confidence interval: 925.15 – 952.02
2658 votes
- Category
- overall
- Evaluated configuration
- chatglm2-6b
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Apache-2.0
0 selected Compare 0