GeekRadar / The comparison desk
COMPARE.
AI models
openai

o4-mini (2025-04-16)

Model evaluation

Capability & preference

Human preference · Arena

Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.

o4-mini (2025-04-16) 1353.2 o4-mini (2025-04-16) · 95% interval 1349.2–1357.1 · 44,801 votes · 2026-11-09

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 · 2026-11-09 · rating

o4-mini (2025-04-16)

1,353.71 rating

Confidence interval: 1,342.76 – 1,364.66

3026 votes

Category
chinese
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,368.14 rating

Confidence interval: 1,361.28 – 1,375.00

8639 votes

Category
coding
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,294.05 rating

Confidence interval: 1,285.87 – 1,302.22

5781 votes

Category
creative_writing
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,367.42 rating

Confidence interval: 1,362.36 – 1,372.48

20809 votes

Category
english
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,314.66 rating

Confidence interval: 1,309.27 – 1,320.05

31647 votes

Category
exclude_ties
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,342.36 rating

Confidence interval: 1,330.12 – 1,354.60

2321 votes

Category
expert
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,363.30 rating

Confidence interval: 1,338.58 – 1,388.02

613 votes

Category
french
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,335.65 rating

Confidence interval: 1,318.21 – 1,353.08

1216 votes

Category
german
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,350.17 rating

Confidence interval: 1,345.03 – 1,355.31

19358 votes

Category
hard_prompts
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,365.46 rating

Confidence interval: 1,358.78 – 1,372.13

9103 votes

Category
hard_prompts_english
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,324.70 rating

Confidence interval: 1,317.22 – 1,332.18

7030 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,307.77 rating

Confidence interval: 1,300.75 – 1,314.79

7970 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,350.13 rating

Confidence interval: 1,338.61 – 1,361.66

2748 votes

Category
industry_legal_and_government
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,353.76 rating

Confidence interval: 1,346.48 – 1,361.04

7524 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,378.72 rating

Confidence interval: 1,367.78 – 1,389.66

2769 votes

Category
industry_mathematical
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,361.39 rating

Confidence interval: 1,349.07 – 1,373.70

2484 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,366.80 rating

Confidence interval: 1,361.12 – 1,372.48

14676 votes

Category
industry_software_and_it_services
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,315.49 rating

Confidence interval: 1,309.00 – 1,321.99

10004 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,320.16 rating

Confidence interval: 1,314.13 – 1,326.20

11871 votes

Category
instruction_following
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,308.52 rating

Confidence interval: 1,289.33 – 1,327.71

1074 votes

Category
japanese
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,312.53 rating

Confidence interval: 1,292.89 – 1,332.17

984 votes

Category
korean
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,314.31 rating

Confidence interval: 1,307.46 – 1,321.17

8609 votes

Category
longer_query
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,389.12 rating

Confidence interval: 1,378.45 – 1,399.79

2906 votes

Category
math
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,349.60 rating

Confidence interval: 1,342.38 – 1,356.83

7743 votes

Category
multi_turn
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,336.29 rating

Confidence interval: 1,331.46 – 1,341.12

23980 votes

Category
non_english
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,353.17 rating

Confidence interval: 1,349.21 – 1,357.13

44801 votes

Category
overall
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,357.64 rating

Confidence interval: 1,345.76 – 1,369.52

2796 votes

Category
polish
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,333.74 rating

Confidence interval: 1,323.92 – 1,343.56

3423 votes

Category
russian
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-11-09 · rating

o4-mini (2025-04-16)

1,345.92 rating

Confidence interval: 1,326.51 – 1,365.33

995 votes

Category
spanish
Evaluated configuration
o4-mini (2025-04-16)
Evaluation type
human preference

Run it locally

Inference · memory estimate

o4-mini (2025-04-16)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary