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 1353.3 o4-mini-2025-04-16 · 95% interval 1349.3–1357.2 · 44,855 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

o4-mini-2025-04-16

1,353.92 rating

Confidence interval: 1,342.99 – 1,364.86

3027 votes

Category
chinese
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,368.14 rating

Confidence interval: 1,361.29 – 1,374.99

8655 votes

Category
coding
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,293.95 rating

Confidence interval: 1,285.79 – 1,302.11

5786 votes

Category
creative_writing
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,367.42 rating

Confidence interval: 1,362.36 – 1,372.48

20833 votes

Category
english
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,314.88 rating

Confidence interval: 1,309.50 – 1,320.27

31675 votes

Category
exclude_ties
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,342.94 rating

Confidence interval: 1,330.74 – 1,355.14

2330 votes

Category
expert
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,363.34 rating

Confidence interval: 1,338.64 – 1,388.04

614 votes

Category
french
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,335.78 rating

Confidence interval: 1,318.36 – 1,353.21

1216 votes

Category
german
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,350.49 rating

Confidence interval: 1,345.35 – 1,355.62

19388 votes

Category
hard_prompts
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,365.74 rating

Confidence interval: 1,359.07 – 1,372.40

9119 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 · 2026-10-15 · rating

o4-mini-2025-04-16

1,324.91 rating

Confidence interval: 1,317.44 – 1,332.39

7033 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 · 2026-10-15 · rating

o4-mini-2025-04-16

1,307.91 rating

Confidence interval: 1,300.89 – 1,314.92

7983 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 · 2026-10-15 · rating

o4-mini-2025-04-16

1,350.02 rating

Confidence interval: 1,338.51 – 1,361.54

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 · 2026-10-15 · rating

o4-mini-2025-04-16

1,353.69 rating

Confidence interval: 1,346.42 – 1,360.95

7542 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 · 2026-10-15 · rating

o4-mini-2025-04-16

1,378.99 rating

Confidence interval: 1,368.08 – 1,389.91

2781 votes

Category
industry_mathematical
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,361.34 rating

Confidence interval: 1,349.05 – 1,373.63

2491 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 · 2026-10-15 · rating

o4-mini-2025-04-16

1,367.02 rating

Confidence interval: 1,361.35 – 1,372.69

14699 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 · 2026-10-15 · rating

o4-mini-2025-04-16

1,315.53 rating

Confidence interval: 1,309.04 – 1,322.02

10012 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 · 2026-10-15 · rating

o4-mini-2025-04-16

1,320.47 rating

Confidence interval: 1,314.45 – 1,326.50

11885 votes

Category
instruction_following
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,308.27 rating

Confidence interval: 1,289.15 – 1,327.40

1075 votes

Category
japanese
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,312.27 rating

Confidence interval: 1,292.67 – 1,331.87

986 votes

Category
korean
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,314.57 rating

Confidence interval: 1,307.72 – 1,321.41

8621 votes

Category
longer_query
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,389.31 rating

Confidence interval: 1,378.66 – 1,399.96

2916 votes

Category
math
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,349.94 rating

Confidence interval: 1,342.72 – 1,357.16

7746 votes

Category
multi_turn
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,336.58 rating

Confidence interval: 1,331.75 – 1,341.40

24010 votes

Category
non_english
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,353.29 rating

Confidence interval: 1,349.34 – 1,357.25

44855 votes

Category
overall
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,357.79 rating

Confidence interval: 1,345.94 – 1,369.64

2795 votes

Category
polish
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,334.32 rating

Confidence interval: 1,324.51 – 1,344.12

3429 votes

Category
russian
Evaluated configuration
o4-mini-2025-04-16
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

o4-mini-2025-04-16

1,346.70 rating

Confidence interval: 1,327.30 – 1,366.11

997 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