GPT-5 Chat (latest)
Closed weights. No supported local deployment or GPU requirement is published.
GeekRadar / The comparison desk
COMPARE.
AI modelsGPT-5 Chat (latest)
AI model Released
- Context window
- 400,000 tokens
- Maximum output
- 128,000 tokens
- Open weights
- No
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
GPT-5 Chat (latest)
1,421.76 rating
Confidence interval: 1,409.44 – 1,434.08
2343 votes
- Category
- chinese
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,397.88 rating
Confidence interval: 1,390.02 – 1,405.75
5984 votes
- Category
- coding
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,364.93 rating
Confidence interval: 1,355.45 – 1,374.41
4017 votes
- Category
- creative_writing
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,405.72 rating
Confidence interval: 1,399.96 – 1,411.49
13290 votes
- Category
- english
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,383.90 rating
Confidence interval: 1,378.08 – 1,389.71
22345 votes
- Category
- exclude_ties
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,403.31 rating
Confidence interval: 1,388.22 – 1,418.41
1540 votes
- Category
- expert
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,409.51 rating
Confidence interval: 1,380.82 – 1,438.20
433 votes
- Category
- french
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,404.32 rating
Confidence interval: 1,381.77 – 1,426.87
702 votes
- Category
- german
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,404.44 rating
Confidence interval: 1,398.91 – 1,409.97
15193 votes
- Category
- hard_prompts
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,403.37 rating
Confidence interval: 1,395.80 – 1,410.93
6625 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,399.43 rating
Confidence interval: 1,391.17 – 1,407.70
5585 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,362.93 rating
Confidence interval: 1,354.88 – 1,370.99
5639 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,431.01 rating
Confidence interval: 1,417.32 – 1,444.70
1902 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,416.34 rating
Confidence interval: 1,407.82 – 1,424.85
5007 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,395.78 rating
Confidence interval: 1,381.07 – 1,410.50
1584 votes
- Category
- industry_mathematical
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,412.63 rating
Confidence interval: 1,398.06 – 1,427.21
1686 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,407.25 rating
Confidence interval: 1,400.97 – 1,413.52
10528 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,384.11 rating
Confidence interval: 1,376.61 – 1,391.61
6780 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,381.08 rating
Confidence interval: 1,374.16 – 1,388.00
8232 votes
- Category
- instruction_following
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,408.91 rating
Confidence interval: 1,381.76 – 1,436.05
524 votes
- Category
- japanese
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,359.81 rating
Confidence interval: 1,338.50 – 1,381.11
822 votes
- Category
- korean
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,398.47 rating
Confidence interval: 1,391.00 – 1,405.94
6841 votes
- Category
- longer_query
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,407.00 rating
Confidence interval: 1,393.33 – 1,420.68
1779 votes
- Category
- math
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,426.15 rating
Confidence interval: 1,417.84 – 1,434.45
5684 votes
- Category
- multi_turn
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,394.59 rating
Confidence interval: 1,389.32 – 1,399.85
17856 votes
- Category
- non_english
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,403.28 rating
Confidence interval: 1,399.01 – 1,407.54
31187 votes
- Category
- overall
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,431.05 rating
Confidence interval: 1,416.48 – 1,445.61
1796 votes
- Category
- polish
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,406.60 rating
Confidence interval: 1,394.21 – 1,418.99
2169 votes
- Category
- russian
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating
GPT-5 Chat (latest)
1,398.92 rating
Confidence interval: 1,378.65 – 1,419.20
901 votes
- Category
- spanish
- Evaluated configuration
- GPT-5 Chat
- Evaluation type
- human preference
Arena text preference / chinesehuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,422.05 rating
Confidence interval: 1,409.72 – 1,434.37
2342 votes
- Category
- chinese
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,398.15 rating
Confidence interval: 1,390.29 – 1,406.01
5988 votes
- Category
- coding
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,365.22 rating
Confidence interval: 1,355.74 – 1,374.71
4015 votes
- Category
- creative_writing
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,405.82 rating
Confidence interval: 1,400.05 – 1,411.58
13290 votes
- Category
- english
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,383.84 rating
Confidence interval: 1,378.02 – 1,389.65
22347 votes
- Category
- exclude_ties
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,403.33 rating
Confidence interval: 1,388.23 – 1,418.42
1540 votes
- Category
- expert
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,409.06 rating
Confidence interval: 1,380.36 – 1,437.76
433 votes
- Category
- french
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,403.90 rating
Confidence interval: 1,381.34 – 1,426.46
701 votes
- Category
- german
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,404.56 rating
Confidence interval: 1,399.03 – 1,410.09
15193 votes
- Category
- hard_prompts
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,403.50 rating
Confidence interval: 1,395.94 – 1,411.06
6627 votes
- Category
- hard_prompts_english
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,399.57 rating
Confidence interval: 1,391.30 – 1,407.83
5586 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,362.90 rating
Confidence interval: 1,354.84 – 1,370.95
5636 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,430.82 rating
Confidence interval: 1,417.12 – 1,444.52
1900 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,416.31 rating
Confidence interval: 1,407.79 – 1,424.82
5009 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,395.75 rating
Confidence interval: 1,381.04 – 1,410.45
1585 votes
- Category
- industry_mathematical
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,412.52 rating
Confidence interval: 1,397.94 – 1,427.11
1684 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,407.41 rating
Confidence interval: 1,401.13 – 1,413.68
10530 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,384.30 rating
Confidence interval: 1,376.80 – 1,391.80
6777 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,381.14 rating
Confidence interval: 1,374.23 – 1,388.06
8236 votes
- Category
- instruction_following
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,408.70 rating
Confidence interval: 1,381.57 – 1,435.84
524 votes
- Category
- japanese
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,359.90 rating
Confidence interval: 1,338.59 – 1,381.22
820 votes
- Category
- korean
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,398.66 rating
Confidence interval: 1,391.19 – 1,406.14
6840 votes
- Category
- longer_query
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,406.84 rating
Confidence interval: 1,393.16 – 1,420.52
1779 votes
- Category
- math
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,426.08 rating
Confidence interval: 1,417.77 – 1,434.38
5682 votes
- Category
- multi_turn
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,394.51 rating
Confidence interval: 1,389.24 – 1,399.78
17857 votes
- Category
- non_english
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,403.20 rating
Confidence interval: 1,398.94 – 1,407.47
31188 votes
- Category
- overall
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,431.18 rating
Confidence interval: 1,416.60 – 1,445.75
1795 votes
- Category
- polish
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,406.54 rating
Confidence interval: 1,394.16 – 1,418.93
2173 votes
- Category
- russian
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating
GPT-5 Chat (latest)
1,398.85 rating
Confidence interval: 1,378.55 – 1,419.16
900 votes
- Category
- spanish
- Evaluated configuration
- gpt-5-chat
- Evaluation type
- human preference
Run it locally
API cost
Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.
GPT-5 Chat (latest)
Capabilities
- Context window
- 400,000 tokens
- Maximum output
- 128,000 tokens
- Reasoning
- Yes
- Tool calling
- No
- Open weights
- No
- Knowledge cutoff
- 2024-09-30
- Model license
- Proprietary
Input modalities
- text
- image
Output modalities
- text
0 selected Compare 0