internlm2_5-20b-chat
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsinternlm2_5-20b-chat
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
internlm2_5-20b-chat
1,199.44 rating
Confidence interval: 1,180.73 – 1,218.14
959 votes
- Category
- chinese
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,158.83 rating
Confidence interval: 1,144.78 – 1,172.87
1684 votes
- Category
- coding
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,122.60 rating
Confidence interval: 1,106.73 – 1,138.47
1432 votes
- Category
- creative_writing
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,202.87 rating
Confidence interval: 1,193.64 – 1,212.10
4966 votes
- Category
- english
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,010.05 rating
Confidence interval: 998.00 – 1,022.10
6447 votes
- Category
- exclude_ties
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,150.39 rating
Confidence interval: 1,128.47 – 1,172.31
604 votes
- Category
- expert
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,062.70 rating
Confidence interval: 1,025.52 – 1,099.87
265 votes
- Category
- german
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,157.90 rating
Confidence interval: 1,146.57 – 1,169.23
2597 votes
- Category
- hard_prompts
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,188.65 rating
Confidence interval: 1,174.20 – 1,203.09
1456 votes
- Category
- hard_prompts_english
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,115.17 rating
Confidence interval: 1,098.36 – 1,131.97
1289 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,103.06 rating
Confidence interval: 1,087.39 – 1,118.74
1427 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,151.20 rating
Confidence interval: 1,128.12 – 1,174.28
685 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,164.87 rating
Confidence interval: 1,150.13 – 1,179.62
1700 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,180.93 rating
Confidence interval: 1,164.62 – 1,197.25
1086 votes
- Category
- industry_mathematical
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,151.66 rating
Confidence interval: 1,126.62 – 1,176.70
548 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,163.63 rating
Confidence interval: 1,151.89 – 1,175.37
2727 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,135.95 rating
Confidence interval: 1,123.87 – 1,148.03
2757 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,134.95 rating
Confidence interval: 1,124.99 – 1,144.91
4092 votes
- Category
- instruction_following
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,148.96 rating
Confidence interval: 1,132.70 – 1,165.23
1266 votes
- Category
- longer_query
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,179.70 rating
Confidence interval: 1,164.94 – 1,194.46
1387 votes
- Category
- math
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,135.53 rating
Confidence interval: 1,120.97 – 1,150.10
1751 votes
- Category
- multi_turn
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,104.33 rating
Confidence interval: 1,094.67 – 1,114.00
4935 votes
- Category
- non_english
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,158.41 rating
Confidence interval: 1,151.36 – 1,165.46
9901 votes
- Category
- overall
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
internlm2_5-20b-chat
1,106.95 rating
Confidence interval: 1,091.26 – 1,122.65
1425 votes
- Category
- russian
- Evaluated configuration
- internlm2_5-20b-chat
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Other
0 selected Compare 0