ChatGLM3 6B
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsChatGLM3 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 · 2026-10-28 · rating
ChatGLM3 6B
1,064.09 rating
Confidence interval: 1,021.49 – 1,106.68
189 votes
- Category
- chinese
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
ChatGLM3 6B
963.89 rating
Confidence interval: 937.88 – 989.91
535 votes
- Category
- coding
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
ChatGLM3 6B
969.73 rating
Confidence interval: 946.81 – 992.65
816 votes
- Category
- creative_writing
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
ChatGLM3 6B
1,002.90 rating
Confidence interval: 990.22 – 1,015.58
3600 votes
- Category
- english
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
ChatGLM3 6B
741.51 rating
Confidence interval: 723.43 – 759.59
3275 votes
- Category
- exclude_ties
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
ChatGLM3 6B
953.04 rating
Confidence interval: 933.24 – 972.85
999 votes
- Category
- hard_prompts
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
ChatGLM3 6B
976.89 rating
Confidence interval: 955.65 – 998.13
835 votes
- Category
- hard_prompts_english
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
ChatGLM3 6B
931.28 rating
Confidence interval: 899.66 – 962.90
378 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
ChatGLM3 6B
928.44 rating
Confidence interval: 905.04 – 951.85
754 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
ChatGLM3 6B
973.51 rating
Confidence interval: 932.51 – 1,014.50
268 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
ChatGLM3 6B
931.73 rating
Confidence interval: 908.82 – 954.65
888 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
ChatGLM3 6B
964.20 rating
Confidence interval: 937.66 – 990.74
466 votes
- Category
- industry_mathematical
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
ChatGLM3 6B
892.25 rating
Confidence interval: 851.27 – 933.24
253 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
ChatGLM3 6B
969.23 rating
Confidence interval: 948.88 – 989.58
1082 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
ChatGLM3 6B
972.47 rating
Confidence interval: 952.33 – 992.60
1108 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
ChatGLM3 6B
953.85 rating
Confidence interval: 936.28 – 971.42
1321 votes
- Category
- instruction_following
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
ChatGLM3 6B
951.57 rating
Confidence interval: 912.43 – 990.72
205 votes
- Category
- longer_query
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
ChatGLM3 6B
989.07 rating
Confidence interval: 965.78 – 1,012.37
576 votes
- Category
- math
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
ChatGLM3 6B
961.78 rating
Confidence interval: 936.20 – 987.36
637 votes
- Category
- multi_turn
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
ChatGLM3 6B
917.56 rating
Confidence interval: 897.20 – 937.91
1058 votes
- Category
- non_english
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
ChatGLM3 6B
972.01 rating
Confidence interval: 960.46 – 983.56
4658 votes
- Category
- overall
- Evaluated configuration
- ChatGLM3 6B
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Apache-2.0
0 selected Compare 0