GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-5.3 Chat

Model evaluation

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 1389.0 GPT-5.3 Chat · 95% interval 1384.8–1393.2 · 34,316 votes · 2026-10-28

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-5.3 Chat

1,431.76 rating

Confidence interval: 1,419.01 – 1,444.51

2280 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,407.54 rating

Confidence interval: 1,400.54 – 1,414.54

9178 votes

Oct 28, 2026

Category: coding
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,355.60 rating

Confidence interval: 1,346.96 – 1,364.24

5340 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,390.02 rating

Confidence interval: 1,384.25 – 1,395.79

15089 votes

Oct 28, 2026

Category: english
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,367.59 rating

Confidence interval: 1,362.11 – 1,373.07

26331 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,396.51 rating

Confidence interval: 1,385.36 – 1,407.66

3017 votes

Oct 28, 2026

Category: expert
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,397.24 rating

Confidence interval: 1,377.79 – 1,416.69

1068 votes

Oct 28, 2026

Category: french
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,385.21 rating

Confidence interval: 1,359.53 – 1,410.89

522 votes

Oct 28, 2026

Category: german
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,398.58 rating

Confidence interval: 1,393.43 – 1,403.74

21646 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,396.58 rating

Confidence interval: 1,389.75 – 1,403.42

9796 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,384.19 rating

Confidence interval: 1,376.43 – 1,391.95

6809 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,356.84 rating

Confidence interval: 1,348.94 – 1,364.74

6710 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,393.87 rating

Confidence interval: 1,381.90 – 1,405.84

2648 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,385.30 rating

Confidence interval: 1,376.82 – 1,393.77

5464 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,385.09 rating

Confidence interval: 1,371.42 – 1,398.75

2019 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,392.45 rating

Confidence interval: 1,380.34 – 1,404.57

2572 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,408.08 rating

Confidence interval: 1,402.02 – 1,414.14

13363 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,377.73 rating

Confidence interval: 1,370.50 – 1,384.96

7969 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,378.24 rating

Confidence interval: 1,371.79 – 1,384.68

11210 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,351.11 rating

Confidence interval: 1,312.52 – 1,389.70

273 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,345.78 rating

Confidence interval: 1,319.19 – 1,372.36

552 votes

Oct 28, 2026

Category: korean
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,395.03 rating

Confidence interval: 1,388.85 – 1,401.21

13418 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,388.78 rating

Confidence interval: 1,375.78 – 1,401.77

2140 votes

Oct 28, 2026

Category: math
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,412.09 rating

Confidence interval: 1,404.11 – 1,420.06

6451 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,382.13 rating

Confidence interval: 1,376.89 – 1,387.37

19227 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,388.98 rating

Confidence interval: 1,384.78 – 1,393.18

34316 votes

Oct 28, 2026

Category: overall
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,396.22 rating

Confidence interval: 1,374.66 – 1,417.79

748 votes

Oct 28, 2026

Category: polish
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,399.22 rating

Confidence interval: 1,389.59 – 1,408.85

4099 votes

Oct 28, 2026

Category: russian
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-28 · rating

GPT-5.3 Chat

1,370.73 rating

Confidence interval: 1,353.29 – 1,388.17

1301 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: GPT-5.3 Chat
Evaluation type: human preference

Run it locally

Inference · memory estimate

GPT-5.3 Chat

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary