GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-5.3 Chat (latest)

AI model Released Mar 3, 2026

Context window: 128,000 tokens
Maximum output: 16,384 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.

GPT-5.3 Chat (latest) 1388.9 gpt-5.3-chat-latest · 95% interval 1384.7–1393.1 · 34,345 votes · 2026-10-15

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-5.3 Chat (latest)

1,432.15 rating

Confidence interval: 1,419.39 – 1,444.90

2283 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,407.55 rating

Confidence interval: 1,400.55 – 1,414.56

9180 votes

Oct 15, 2026

Category: coding
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,354.77 rating

Confidence interval: 1,346.13 – 1,363.42

5348 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,390.24 rating

Confidence interval: 1,384.46 – 1,396.01

15098 votes

Oct 15, 2026

Category: english
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,367.49 rating

Confidence interval: 1,362.01 – 1,372.98

26356 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,396.53 rating

Confidence interval: 1,385.37 – 1,407.69

3017 votes

Oct 15, 2026

Category: expert
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,397.52 rating

Confidence interval: 1,378.06 – 1,416.97

1073 votes

Oct 15, 2026

Category: french
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,384.37 rating

Confidence interval: 1,358.65 – 1,410.08

523 votes

Oct 15, 2026

Category: german
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,398.48 rating

Confidence interval: 1,393.32 – 1,403.64

21658 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,396.73 rating

Confidence interval: 1,389.89 – 1,403.57

9796 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,384.32 rating

Confidence interval: 1,376.56 – 1,392.08

6815 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,356.69 rating

Confidence interval: 1,348.79 – 1,364.59

6717 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,394.24 rating

Confidence interval: 1,382.27 – 1,406.22

2652 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,385.10 rating

Confidence interval: 1,376.62 – 1,393.58

5465 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,384.42 rating

Confidence interval: 1,370.75 – 1,398.09

2022 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,392.08 rating

Confidence interval: 1,379.96 – 1,404.20

2574 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,408.00 rating

Confidence interval: 1,401.94 – 1,414.06

13372 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,377.20 rating

Confidence interval: 1,369.97 – 1,384.44

7970 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,378.00 rating

Confidence interval: 1,371.55 – 1,384.46

11216 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,352.20 rating

Confidence interval: 1,313.66 – 1,390.75

274 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,345.79 rating

Confidence interval: 1,319.19 – 1,372.40

552 votes

Oct 15, 2026

Category: korean
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,395.09 rating

Confidence interval: 1,388.90 – 1,401.27

13426 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,388.72 rating

Confidence interval: 1,375.71 – 1,401.73

2139 votes

Oct 15, 2026

Category: math
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,411.97 rating

Confidence interval: 1,403.99 – 1,419.95

6452 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,381.88 rating

Confidence interval: 1,376.64 – 1,387.13

19247 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,388.89 rating

Confidence interval: 1,384.69 – 1,393.09

34345 votes

Oct 15, 2026

Category: overall
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,396.15 rating

Confidence interval: 1,374.57 – 1,417.73

746 votes

Oct 15, 2026

Category: polish
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,398.94 rating

Confidence interval: 1,389.30 – 1,408.57

4099 votes

Oct 15, 2026

Category: russian
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-15 · rating

GPT-5.3 Chat (latest)

1,370.77 rating

Confidence interval: 1,353.29 – 1,388.25

1300 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: gpt-5.3-chat-latest
Evaluation type: human preference

Run it locally

Inference · memory estimate

GPT-5.3 Chat (latest)

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

GPT-5.3 Chat (latest)

Provider offer

Capabilities

Context window: 128,000 tokens
Maximum output: 16,384 tokens
Reasoning: No
Tool calling: Yes
Open weights: No
Knowledge cutoff: 2025-08-31
Model license: Proprietary

Input modalities

text
image

Output modalities

text