GeekRadar / The comparison desk
COMPARE.
AI models
openai

o1 (2024-12-17)

Model evaluation

Capability & preference

Human preference · Arena

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

o1 (2024-12-17) 1365.8 o1 (2024-12-17) · 95% interval 1361.3–1370.3 · 27,807 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

o1 (2024-12-17)

1,393.83 rating

Confidence interval: 1,379.46 – 1,408.19

1780 votes

Category
chinese
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / codinghuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,366.62 rating

Confidence interval: 1,357.07 – 1,376.17

3973 votes

Category
coding
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / creative_writinghuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,347.15 rating

Confidence interval: 1,338.11 – 1,356.19

4642 votes

Category
creative_writing
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / englishhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,372.20 rating

Confidence interval: 1,366.65 – 1,377.75

16316 votes

Category
english
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / exclude_tieshuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,333.47 rating

Confidence interval: 1,327.05 – 1,339.90

19214 votes

Category
exclude_ties
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / experthuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,361.25 rating

Confidence interval: 1,344.43 – 1,378.06

1330 votes

Category
expert
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / frenchhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,344.23 rating

Confidence interval: 1,307.28 – 1,381.18

252 votes

Category
french
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / germanhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,336.83 rating

Confidence interval: 1,312.63 – 1,361.03

556 votes

Category
german
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / hard_promptshuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,371.35 rating

Confidence interval: 1,363.69 – 1,379.01

6453 votes

Category
hard_prompts
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,372.03 rating

Confidence interval: 1,362.66 – 1,381.40

4238 votes

Category
hard_prompts_english
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,327.54 rating

Confidence interval: 1,315.93 – 1,339.15

2720 votes

Category
industry_business_and_management_and_financial_operations
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,357.99 rating

Confidence interval: 1,349.44 – 1,366.54

5210 votes

Category
industry_entertainment_and_sports_and_media
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,368.29 rating

Confidence interval: 1,352.57 – 1,384.01

1454 votes

Category
industry_legal_and_government
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,368.78 rating

Confidence interval: 1,359.92 – 1,377.63

4820 votes

Category
industry_life_and_physical_and_social_science
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / industry_mathematicalhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,389.54 rating

Confidence interval: 1,378.05 – 1,401.03

2644 votes

Category
industry_mathematical
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,354.79 rating

Confidence interval: 1,337.76 – 1,371.82

1273 votes

Category
industry_medicine_and_healthcare
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,366.27 rating

Confidence interval: 1,358.60 – 1,373.94

6584 votes

Category
industry_software_and_it_services
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,359.96 rating

Confidence interval: 1,352.65 – 1,367.27

7663 votes

Category
industry_writing_and_literature_and_language
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / instruction_followinghuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,367.18 rating

Confidence interval: 1,360.67 – 1,373.70

10246 votes

Category
instruction_following
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / japanesehuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,346.11 rating

Confidence interval: 1,320.07 – 1,372.15

581 votes

Category
japanese
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / koreanhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,396.06 rating

Confidence interval: 1,364.34 – 1,427.79

396 votes

Category
korean
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / longer_queryhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,377.47 rating

Confidence interval: 1,367.62 – 1,387.33

3571 votes

Category
longer_query
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / mathhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,388.38 rating

Confidence interval: 1,377.56 – 1,399.20

2986 votes

Category
math
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / multi_turnhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,354.75 rating

Confidence interval: 1,345.56 – 1,363.93

4399 votes

Category
multi_turn
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / non_englishhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,358.36 rating

Confidence interval: 1,352.27 – 1,364.45

11491 votes

Category
non_english
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / overallhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,365.79 rating

Confidence interval: 1,361.32 – 1,370.27

27807 votes

Category
overall
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / russianhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,355.59 rating

Confidence interval: 1,345.05 – 1,366.13

3078 votes

Category
russian
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference
Arena text preference / spanishhuman preference · 2026-10-28 · rating

o1 (2024-12-17)

1,345.08 rating

Confidence interval: 1,296.87 – 1,393.29

142 votes

Category
spanish
Evaluated configuration
o1 (2024-12-17)
Evaluation type
human preference

Run it locally

Inference · memory estimate

o1 (2024-12-17)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license
Proprietary