GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-4o (2024-05-13)

AI model Released May 13, 2024

Context window: 128,000 tokens
Maximum output: 4,096 tokens
Open weights: No

Capability & preference

Human preference · Arena

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

GPT-4o (2024-05-13) 1300.4 GPT-4o (2024-05-13) · 95% interval 1297.0–1303.8 · 112,881 votes · 2026-10-28

Model performance

Radar task score: four tests, equal weight. An experimental summary of these tasks, not a universal intelligence rating.

GPT-4o (2024-05-13)

Tested configuration Radar task score

Unrated

1/4 core tests · not enough evidence

1 benchmark results for this configuration

Scientific reasoning

GPQA Diamond · 25%

Expert-written science questions; strict multiple-choice scoring. Chance accuracy is 25%.

GPT-4o (2024-05-13) 48.9^*% Approx. 95% interval: 43.7–54.0% · 2025-01-27 · Older result

Novel problem solving

Mystery Game Puzzles · 25%

Best-next-move puzzles in an undisclosed game variant. A narrow reasoning test, not general intelligence.

GPT-4o (2024-05-13) Not available

Advanced mathematics

FrontierMath Tiers 1-3 · 25%

Private v2 mathematics problems with Python tools. Earlier versions and Tier 4 are excluded.

GPT-4o (2024-05-13) Not available

Factual answers

SimpleQA Verified · 25%

Correct factual answers under a guessing prompt, graded by a model. Not a hallucination or abstention score.

GPT-4o (2024-05-13) Not available

Bars show reported task scores. Whiskers are approximate 95% intervals where standard errors are available. Different reasoning budgets are not equal-cost tests. Missing results are never zero.

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.

Test version

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

GPT-4o (2024-05-13)

1,277.18 rating

Confidence interval: 1,268.51 – 1,285.85

11416 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,296.86 rating

Confidence interval: 1,290.45 – 1,303.26

19526 votes

Oct 28, 2026

Category: coding
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,291.15 rating

Confidence interval: 1,284.06 – 1,298.25

16599 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,312.35 rating

Confidence interval: 1,307.76 – 1,316.94

60226 votes

Oct 28, 2026

Category: english
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,238.14 rating

Confidence interval: 1,232.70 – 1,243.58

74322 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,249.76 rating

Confidence interval: 1,239.60 – 1,259.91

5887 votes

Oct 28, 2026

Category: expert
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,304.44 rating

Confidence interval: 1,283.34 – 1,325.54

1359 votes

Oct 28, 2026

Category: french
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,282.44 rating

Confidence interval: 1,268.76 – 1,296.12

3573 votes

Oct 28, 2026

Category: german
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,280.67 rating

Confidence interval: 1,275.33 – 1,286.02

32416 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,292.64 rating

Confidence interval: 1,286.26 – 1,299.02

19579 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,261.50 rating

Confidence interval: 1,253.96 – 1,269.05

13299 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,289.39 rating

Confidence interval: 1,282.58 – 1,296.20

17607 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,313.75 rating

Confidence interval: 1,303.66 – 1,323.83

6743 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,294.85 rating

Confidence interval: 1,288.14 – 1,301.55

19017 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,284.27 rating

Confidence interval: 1,276.98 – 1,291.56

13306 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,277.88 rating

Confidence interval: 1,267.18 – 1,288.59

5984 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,297.15 rating

Confidence interval: 1,291.59 – 1,302.72

31401 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,297.68 rating

Confidence interval: 1,291.84 – 1,303.52

29959 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,277.50 rating

Confidence interval: 1,272.51 – 1,282.50

43766 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,256.87 rating

Confidence interval: 1,241.40 – 1,272.33

2674 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,233.81 rating

Confidence interval: 1,216.34 – 1,251.28

3517 votes

Oct 28, 2026

Category: korean
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,288.29 rating

Confidence interval: 1,281.40 – 1,295.17

14922 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,284.35 rating

Confidence interval: 1,277.45 – 1,291.25

15103 votes

Oct 28, 2026

Category: math
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,301.63 rating

Confidence interval: 1,294.97 – 1,308.28

20434 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,282.67 rating

Confidence interval: 1,277.95 – 1,287.40

52655 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,300.41 rating

Confidence interval: 1,296.98 – 1,303.85

112881 votes

Oct 28, 2026

Category: overall
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,364.63 rating

Confidence interval: 1,307.97 – 1,421.28

166 votes

Oct 28, 2026

Category: polish
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,285.36 rating

Confidence interval: 1,277.95 – 1,292.77

13904 votes

Oct 28, 2026

Category: russian
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

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

GPT-4o (2024-05-13)

1,292.16 rating

Confidence interval: 1,271.98 – 1,312.34

1712 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: GPT-4o (2024-05-13)
Evaluation type: human preference

Arena text preference / chinesehuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,277.23 rating

Confidence interval: 1,268.56 – 1,285.90

11416 votes

Oct 15, 2026

Category: chinese
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,296.96 rating

Confidence interval: 1,290.55 – 1,303.37

19526 votes

Oct 15, 2026

Category: coding
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,291.31 rating

Confidence interval: 1,284.21 – 1,298.41

16599 votes

Oct 15, 2026

Category: creative_writing
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,312.30 rating

Confidence interval: 1,307.71 – 1,316.88

60226 votes

Oct 15, 2026

Category: english
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,238.15 rating

Confidence interval: 1,232.71 – 1,243.58

74322 votes

Oct 15, 2026

Category: exclude_ties
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,249.80 rating

Confidence interval: 1,239.63 – 1,259.96

5887 votes

Oct 15, 2026

Category: expert
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,304.12 rating

Confidence interval: 1,283.00 – 1,325.25

1359 votes

Oct 15, 2026

Category: french
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,282.44 rating

Confidence interval: 1,268.83 – 1,296.05

3573 votes

Oct 15, 2026

Category: german
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,280.66 rating

Confidence interval: 1,275.32 – 1,286.01

32416 votes

Oct 15, 2026

Category: hard_prompts
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,292.53 rating

Confidence interval: 1,286.14 – 1,298.91

19579 votes

Oct 15, 2026

Category: hard_prompts_english
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,261.54 rating

Confidence interval: 1,253.99 – 1,269.09

13299 votes

Oct 15, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,289.45 rating

Confidence interval: 1,282.64 – 1,296.26

17607 votes

Oct 15, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,313.49 rating

Confidence interval: 1,303.41 – 1,323.58

6743 votes

Oct 15, 2026

Category: industry_legal_and_government
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,294.83 rating

Confidence interval: 1,288.12 – 1,301.54

19017 votes

Oct 15, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,284.26 rating

Confidence interval: 1,276.98 – 1,291.54

13306 votes

Oct 15, 2026

Category: industry_mathematical
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,277.94 rating

Confidence interval: 1,267.23 – 1,288.65

5984 votes

Oct 15, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,297.24 rating

Confidence interval: 1,291.67 – 1,302.80

31401 votes

Oct 15, 2026

Category: industry_software_and_it_services
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,297.75 rating

Confidence interval: 1,291.90 – 1,303.59

29959 votes

Oct 15, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,277.51 rating

Confidence interval: 1,272.52 – 1,282.51

43766 votes

Oct 15, 2026

Category: instruction_following
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,256.70 rating

Confidence interval: 1,241.32 – 1,272.07

2674 votes

Oct 15, 2026

Category: japanese
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,233.85 rating

Confidence interval: 1,216.41 – 1,251.29

3517 votes

Oct 15, 2026

Category: korean
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,288.33 rating

Confidence interval: 1,281.44 – 1,295.21

14922 votes

Oct 15, 2026

Category: longer_query
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,284.31 rating

Confidence interval: 1,277.41 – 1,291.20

15103 votes

Oct 15, 2026

Category: math
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,301.62 rating

Confidence interval: 1,294.96 – 1,308.28

20434 votes

Oct 15, 2026

Category: multi_turn
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,282.76 rating

Confidence interval: 1,278.04 – 1,287.49

52655 votes

Oct 15, 2026

Category: non_english
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,300.40 rating

Confidence interval: 1,296.96 – 1,303.83

112881 votes

Oct 15, 2026

Category: overall
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,364.73 rating

Confidence interval: 1,307.93 – 1,421.52

166 votes

Oct 15, 2026

Category: polish
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,285.51 rating

Confidence interval: 1,278.10 – 1,292.93

13904 votes

Oct 15, 2026

Category: russian
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-10-15 · rating

GPT-4o (2024-05-13)

1,292.08 rating

Confidence interval: 1,271.87 – 1,312.29

1712 votes

Oct 15, 2026

Category: spanish
Evaluated configuration: gpt-4o-2024-05-13
Evaluation type: human preference

Run it locally

Inference · memory estimate

GPT-4o (2024-05-13)

Closed weights. No supported local deployment or GPU requirement is published.

API cost

USD / month

Input tokens / monthOutput tokens / month

Standard text-token estimate. Excludes taxes, caching, batch discounts, reasoning and multimodal surcharges. Provider limits and regional availability may differ.

GPT-4o (2024-05-13)

Provider offer

Capabilities

Context window: 128,000 tokens
Maximum output: 4,096 tokens
Reasoning: No
Tool calling: Yes
Open weights: No
Knowledge cutoff: 2023-09
Model license: Proprietary

Input modalities

text
image

Output modalities

text

* Provisional data