gpt-4-0125-preview
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsgpt-4-0125-preview
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
gpt-4-0125-preview
1,237.51 rating
Confidence interval: 1,227.72 – 1,247.30
11382 votes
- Category
- chinese
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,248.98 rating
Confidence interval: 1,241.42 – 1,256.54
15289 votes
- Category
- coding
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,232.27 rating
Confidence interval: 1,224.16 – 1,240.38
13940 votes
- Category
- creative_writing
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,276.05 rating
Confidence interval: 1,270.96 – 1,281.15
54967 votes
- Category
- english
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,171.43 rating
Confidence interval: 1,165.27 – 1,177.60
63519 votes
- Category
- exclude_ties
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,205.17 rating
Confidence interval: 1,193.21 – 1,217.13
4454 votes
- Category
- expert
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,281.04 rating
Confidence interval: 1,258.89 – 1,303.19
1516 votes
- Category
- french
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,245.50 rating
Confidence interval: 1,230.22 – 1,260.78
2668 votes
- Category
- german
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,238.41 rating
Confidence interval: 1,232.29 – 1,244.52
25575 votes
- Category
- hard_prompts
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,251.09 rating
Confidence interval: 1,243.85 – 1,258.32
16792 votes
- Category
- hard_prompts_english
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,216.58 rating
Confidence interval: 1,207.76 – 1,225.40
9697 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,236.96 rating
Confidence interval: 1,229.07 – 1,244.85
13994 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,260.67 rating
Confidence interval: 1,248.97 – 1,272.36
5037 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,249.80 rating
Confidence interval: 1,242.07 – 1,257.54
16044 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,260.96 rating
Confidence interval: 1,252.66 – 1,269.26
10830 votes
- Category
- industry_mathematical
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,231.48 rating
Confidence interval: 1,219.59 – 1,243.36
5155 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,249.51 rating
Confidence interval: 1,243.09 – 1,255.93
25603 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,257.20 rating
Confidence interval: 1,250.54 – 1,263.86
23492 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,234.86 rating
Confidence interval: 1,229.11 – 1,240.60
33252 votes
- Category
- instruction_following
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,195.13 rating
Confidence interval: 1,176.51 – 1,213.75
1474 votes
- Category
- japanese
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,173.59 rating
Confidence interval: 1,152.55 – 1,194.63
1393 votes
- Category
- korean
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,243.56 rating
Confidence interval: 1,235.05 – 1,252.08
9653 votes
- Category
- longer_query
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,267.74 rating
Confidence interval: 1,259.86 – 1,275.63
12374 votes
- Category
- math
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,250.38 rating
Confidence interval: 1,242.55 – 1,258.22
14381 votes
- Category
- multi_turn
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,240.82 rating
Confidence interval: 1,235.36 – 1,246.28
38472 votes
- Category
- non_english
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,262.17 rating
Confidence interval: 1,258.09 – 1,266.24
93439 votes
- Category
- overall
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,299.23 rating
Confidence interval: 1,246.19 – 1,352.27
215 votes
- Category
- polish
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,240.94 rating
Confidence interval: 1,232.03 – 1,249.84
8356 votes
- Category
- russian
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
gpt-4-0125-preview
1,247.45 rating
Confidence interval: 1,224.92 – 1,269.99
1219 votes
- Category
- spanish
- Evaluated configuration
- gpt-4-0125-preview
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Proprietary
0 selected Compare 0