GPT-4.5 Preview (2025-02-27)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsGPT-4.5 Preview (2025-02-27)
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-4.5 Preview (2025-02-27)
1,421.07 rating
Confidence interval: 1,401.55 – 1,440.59
907 votes
- Category
- chinese
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,396.28 rating
Confidence interval: 1,383.34 – 1,409.22
1939 votes
- Category
- coding
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,393.53 rating
Confidence interval: 1,381.57 – 1,405.48
2618 votes
- Category
- creative_writing
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,419.72 rating
Confidence interval: 1,412.62 – 1,426.82
8425 votes
- Category
- english
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,410.82 rating
Confidence interval: 1,402.35 – 1,419.30
10031 votes
- Category
- exclude_ties
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,394.14 rating
Confidence interval: 1,370.87 – 1,417.41
608 votes
- Category
- expert
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,418.20 rating
Confidence interval: 1,362.38 – 1,474.02
121 votes
- Category
- french
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,456.60 rating
Confidence interval: 1,424.07 – 1,489.12
319 votes
- Category
- german
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,403.31 rating
Confidence interval: 1,393.35 – 1,413.26
3445 votes
- Category
- hard_prompts
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,406.50 rating
Confidence interval: 1,394.24 – 1,418.75
2260 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,385.54 rating
Confidence interval: 1,369.84 – 1,401.24
1394 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,399.25 rating
Confidence interval: 1,387.46 – 1,411.05
2627 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,433.70 rating
Confidence interval: 1,411.14 – 1,456.26
701 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,420.21 rating
Confidence interval: 1,408.40 – 1,432.03
2545 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,410.45 rating
Confidence interval: 1,394.86 – 1,426.03
1283 votes
- Category
- industry_mathematical
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,410.76 rating
Confidence interval: 1,386.46 – 1,435.06
589 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,411.94 rating
Confidence interval: 1,401.81 – 1,422.08
3358 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,411.53 rating
Confidence interval: 1,401.88 – 1,421.18
4092 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,403.71 rating
Confidence interval: 1,395.41 – 1,412.00
5501 votes
- Category
- instruction_following
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,415.87 rating
Confidence interval: 1,377.52 – 1,454.21
271 votes
- Category
- japanese
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,392.17 rating
Confidence interval: 1,348.60 – 1,435.74
215 votes
- Category
- korean
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,405.57 rating
Confidence interval: 1,391.98 – 1,419.16
1796 votes
- Category
- longer_query
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,412.05 rating
Confidence interval: 1,396.84 – 1,427.26
1393 votes
- Category
- math
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,443.94 rating
Confidence interval: 1,430.50 – 1,457.39
2052 votes
- Category
- multi_turn
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,412.79 rating
Confidence interval: 1,404.83 – 1,420.76
6122 votes
- Category
- non_english
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,417.35 rating
Confidence interval: 1,411.66 – 1,423.03
14547 votes
- Category
- overall
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating
GPT-4.5 Preview (2025-02-27)
1,419.00 rating
Confidence interval: 1,403.55 – 1,434.45
1430 votes
- Category
- russian
- Evaluated configuration
- GPT-4.5 Preview (2025-02-27)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Proprietary
0 selected Compare 0