GPT-4 Turbo Preview (1106)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsGPT-4 Turbo Preview (1106)
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 · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,242.50 rating
Confidence interval: 1,232.51 – 1,252.48
9150 votes
- Category
- chinese
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,253.75 rating
Confidence interval: 1,246.40 – 1,261.09
15605 votes
- Category
- coding
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,243.97 rating
Confidence interval: 1,236.07 – 1,251.87
15576 votes
- Category
- creative_writing
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,277.12 rating
Confidence interval: 1,272.24 – 1,282.01
64698 votes
- Category
- english
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,173.83 rating
Confidence interval: 1,167.90 – 1,179.75
69044 votes
- Category
- exclude_ties
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,211.15 rating
Confidence interval: 1,199.25 – 1,223.06
4240 votes
- Category
- expert
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,282.78 rating
Confidence interval: 1,261.47 – 1,304.09
1734 votes
- Category
- french
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,250.53 rating
Confidence interval: 1,234.94 – 1,266.13
2503 votes
- Category
- german
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,240.99 rating
Confidence interval: 1,235.01 – 1,246.97
26242 votes
- Category
- hard_prompts
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,253.69 rating
Confidence interval: 1,246.62 – 1,260.76
18316 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,210.83 rating
Confidence interval: 1,202.10 – 1,219.57
9573 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,242.50 rating
Confidence interval: 1,234.80 – 1,250.20
15221 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,249.40 rating
Confidence interval: 1,237.95 – 1,260.84
5572 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,254.81 rating
Confidence interval: 1,247.20 – 1,262.41
17680 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,270.20 rating
Confidence interval: 1,261.98 – 1,278.42
11549 votes
- Category
- industry_mathematical
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,224.23 rating
Confidence interval: 1,212.36 – 1,236.11
5514 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,250.00 rating
Confidence interval: 1,243.77 – 1,256.24
26445 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,264.29 rating
Confidence interval: 1,257.80 – 1,270.78
24682 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,240.47 rating
Confidence interval: 1,234.86 – 1,246.07
34416 votes
- Category
- instruction_following
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,209.31 rating
Confidence interval: 1,190.54 – 1,228.09
1422 votes
- Category
- japanese
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,184.12 rating
Confidence interval: 1,162.67 – 1,205.57
1292 votes
- Category
- korean
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,235.74 rating
Confidence interval: 1,227.34 – 1,244.14
9140 votes
- Category
- longer_query
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,269.21 rating
Confidence interval: 1,261.37 – 1,277.04
13306 votes
- Category
- math
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,256.59 rating
Confidence interval: 1,248.81 – 1,264.36
14867 votes
- Category
- multi_turn
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,245.51 rating
Confidence interval: 1,240.11 – 1,250.92
35407 votes
- Category
- non_english
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,263.40 rating
Confidence interval: 1,259.54 – 1,267.26
100105 votes
- Category
- overall
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,326.41 rating
Confidence interval: 1,270.75 – 1,382.06
193 votes
- Category
- polish
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,251.30 rating
Confidence interval: 1,242.13 – 1,260.48
7053 votes
- Category
- russian
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating
GPT-4 Turbo Preview (1106)
1,260.97 rating
Confidence interval: 1,239.00 – 1,282.94
1472 votes
- Category
- spanish
- Evaluated configuration
- GPT-4 Turbo Preview (1106)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Proprietary
0 selected Compare 0