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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,199.39 rating
Confidence interval: 1,180.69 – 1,218.09
959 votes
- Category
- chinese
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,158.73 rating
Confidence interval: 1,144.69 – 1,172.77
1684 votes
- Category
- coding
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,122.45 rating
Confidence interval: 1,106.58 – 1,138.31
1432 votes
- Category
- creative_writing
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,202.92 rating
Confidence interval: 1,193.69 – 1,212.15
4966 votes
- Category
- english
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,010.04 rating
Confidence interval: 997.99 – 1,022.09
6447 votes
- Category
- exclude_ties
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,150.35 rating
Confidence interval: 1,128.43 – 1,172.26
604 votes
- Category
- expert
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,062.70 rating
Confidence interval: 1,025.50 – 1,099.89
265 votes
- Category
- german
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,157.91 rating
Confidence interval: 1,146.58 – 1,169.24
2597 votes
- Category
- hard_prompts
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,188.76 rating
Confidence interval: 1,174.32 – 1,203.20
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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,115.13 rating
Confidence interval: 1,098.32 – 1,131.93
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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,103.00 rating
Confidence interval: 1,087.33 – 1,118.68
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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,151.46 rating
Confidence interval: 1,128.38 – 1,174.54
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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,164.89 rating
Confidence interval: 1,150.15 – 1,179.64
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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,180.94 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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,151.60 rating
Confidence interval: 1,126.56 – 1,176.64
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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,163.55 rating
Confidence interval: 1,151.81 – 1,175.29
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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,135.89 rating
Confidence interval: 1,123.81 – 1,147.96
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 · 2026-10-28 · rating
InternLM2.5 20B Chat
1,134.94 rating
Confidence interval: 1,124.98 – 1,144.90
4092 votes
- Category
- instruction_following
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,148.92 rating
Confidence interval: 1,132.66 – 1,165.18
1266 votes
- Category
- longer_query
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,179.74 rating
Confidence interval: 1,164.98 – 1,194.50
1387 votes
- Category
- math
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,135.54 rating
Confidence interval: 1,120.98 – 1,150.10
1751 votes
- Category
- multi_turn
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,104.24 rating
Confidence interval: 1,094.57 – 1,113.91
4935 votes
- Category
- non_english
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,158.42 rating
Confidence interval: 1,151.37 – 1,165.47
9901 votes
- Category
- overall
- Evaluated configuration
- InternLM2.5 20B Chat
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
InternLM2.5 20B Chat
1,106.80 rating
Confidence interval: 1,091.11 – 1,122.49
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