GeekRadar / The comparison desk
COMPARE.
AI models
openai

o3-2025-04-16

Model evaluation

Capability & preference

Human preference · Arena

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

o3-2025-04-16 1409.8 o3-2025-04-16 · 95% interval 1406.2–1413.4 · 58,908 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

o3-2025-04-16

1,437.05 rating

Confidence interval: 1,427.11 – 1,446.99

3891 votes

Category
chinese
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-15 · rating

o3-2025-04-16

1,407.45 rating

Confidence interval: 1,401.28 – 1,413.63

11583 votes

Category
coding
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

o3-2025-04-16

1,358.53 rating

Confidence interval: 1,351.26 – 1,365.81

7636 votes

Category
creative_writing
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,416.44 rating

Confidence interval: 1,411.75 – 1,421.13

27283 votes

Category
english
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

o3-2025-04-16

1,393.04 rating

Confidence interval: 1,388.11 – 1,397.97

42875 votes

Category
exclude_ties
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-15 · rating

o3-2025-04-16

1,402.12 rating

Confidence interval: 1,390.88 – 1,413.36

3020 votes

Category
expert
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,430.06 rating

Confidence interval: 1,408.03 – 1,452.08

826 votes

Category
french
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,419.75 rating

Confidence interval: 1,403.73 – 1,435.76

1508 votes

Category
german
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

o3-2025-04-16

1,402.05 rating

Confidence interval: 1,397.28 – 1,406.81

25530 votes

Category
hard_prompts
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,410.56 rating

Confidence interval: 1,404.45 – 1,416.67

12107 votes

Category
hard_prompts_english
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

o3-2025-04-16

1,392.65 rating

Confidence interval: 1,385.84 – 1,399.46

9485 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

o3-2025-04-16

1,372.69 rating

Confidence interval: 1,366.27 – 1,379.11

10508 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

o3-2025-04-16

1,427.80 rating

Confidence interval: 1,417.62 – 1,437.97

3745 votes

Category
industry_legal_and_government
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

o3-2025-04-16

1,429.33 rating

Confidence interval: 1,422.62 – 1,436.04

9925 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,422.66 rating

Confidence interval: 1,412.40 – 1,432.92

3457 votes

Category
industry_mathematical
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

o3-2025-04-16

1,447.39 rating

Confidence interval: 1,436.36 – 1,458.42

3325 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

o3-2025-04-16

1,414.75 rating

Confidence interval: 1,409.53 – 1,419.97

19145 votes

Category
industry_software_and_it_services
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

o3-2025-04-16

1,371.44 rating

Confidence interval: 1,365.53 – 1,377.36

13240 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

o3-2025-04-16

1,367.74 rating

Confidence interval: 1,362.21 – 1,373.28

15503 votes

Category
instruction_following
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-15 · rating

o3-2025-04-16

1,403.62 rating

Confidence interval: 1,386.20 – 1,421.03

1419 votes

Category
japanese
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,370.24 rating

Confidence interval: 1,352.01 – 1,388.46

1200 votes

Category
korean
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,371.61 rating

Confidence interval: 1,365.49 – 1,377.73

11540 votes

Category
longer_query
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,426.41 rating

Confidence interval: 1,416.46 – 1,436.35

3701 votes

Category
math
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,404.63 rating

Confidence interval: 1,397.86 – 1,411.40

9655 votes

Category
multi_turn
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,401.22 rating

Confidence interval: 1,396.73 – 1,405.70

31572 votes

Category
non_english
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,409.82 rating

Confidence interval: 1,406.21 – 1,413.43

58908 votes

Category
overall
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / polishhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,437.93 rating

Confidence interval: 1,427.19 – 1,448.67

3834 votes

Category
polish
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,406.27 rating

Confidence interval: 1,397.53 – 1,415.01

4682 votes

Category
russian
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-15 · rating

o3-2025-04-16

1,394.75 rating

Confidence interval: 1,376.84 – 1,412.66

1221 votes

Category
spanish
Evaluated configuration
o3-2025-04-16
Evaluation type
human preference

Run it locally

Inference · memory estimate

o3-2025-04-16

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary