GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-4 Turbo (2024-04-09)

Model evaluation

Capability & preference

Human preference · Arena

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

GPT-4 Turbo (2024-04-09) 1271.7 GPT-4 Turbo (2024-04-09) · 95% interval 1267.8–1275.6 · 98,114 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

GPT-4 Turbo (2024-04-09)

1,242.39 rating

Confidence interval: 1,232.95 – 1,251.82

10827 votes

Nov 9, 2026

Category: chinese
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,268.20 rating

Confidence interval: 1,261.10 – 1,275.30

17104 votes

Nov 9, 2026

Category: coding
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,268.37 rating

Confidence interval: 1,260.65 – 1,276.09

14396 votes

Nov 9, 2026

Category: creative_writing
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,291.15 rating

Confidence interval: 1,286.27 – 1,296.03

55116 votes

Nov 9, 2026

Category: english
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,190.07 rating

Confidence interval: 1,184.22 – 1,195.93

65114 votes

Nov 9, 2026

Category: exclude_ties
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,222.79 rating

Confidence interval: 1,211.71 – 1,233.86

5195 votes

Nov 9, 2026

Category: expert
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,275.22 rating

Confidence interval: 1,253.37 – 1,297.08

1402 votes

Nov 9, 2026

Category: french
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,259.30 rating

Confidence interval: 1,244.77 – 1,273.82

3359 votes

Nov 9, 2026

Category: german
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,250.75 rating

Confidence interval: 1,244.88 – 1,256.61

28310 votes

Nov 9, 2026

Category: hard_prompts
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,265.93 rating

Confidence interval: 1,258.96 – 1,272.89

17922 votes

Nov 9, 2026

Category: hard_prompts_english
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,222.25 rating

Confidence interval: 1,213.80 – 1,230.70

10807 votes

Nov 9, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,258.19 rating

Confidence interval: 1,250.76 – 1,265.63

14793 votes

Nov 9, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,264.93 rating

Confidence interval: 1,253.78 – 1,276.07

5381 votes

Nov 9, 2026

Category: industry_legal_and_government
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,255.69 rating

Confidence interval: 1,248.32 – 1,263.06

16354 votes

Nov 9, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,268.03 rating

Confidence interval: 1,260.02 – 1,276.04

11796 votes

Nov 9, 2026

Category: industry_mathematical
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,239.35 rating

Confidence interval: 1,227.73 – 1,250.96

5046 votes

Nov 9, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,267.02 rating

Confidence interval: 1,260.88 – 1,273.15

27573 votes

Nov 9, 2026

Category: industry_software_and_it_services
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,278.64 rating

Confidence interval: 1,272.22 – 1,285.06

24529 votes

Nov 9, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,249.27 rating

Confidence interval: 1,243.77 – 1,254.76

36297 votes

Nov 9, 2026

Category: instruction_following
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,194.11 rating

Confidence interval: 1,177.38 – 1,210.83

2112 votes

Nov 9, 2026

Category: japanese
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,186.78 rating

Confidence interval: 1,168.10 – 1,205.47

2668 votes

Nov 9, 2026

Category: korean
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,253.57 rating

Confidence interval: 1,245.73 – 1,261.42

11559 votes

Nov 9, 2026

Category: longer_query
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,271.58 rating

Confidence interval: 1,263.94 – 1,279.22

13217 votes

Nov 9, 2026

Category: math
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,266.84 rating

Confidence interval: 1,259.40 – 1,274.29

15255 votes

Nov 9, 2026

Category: multi_turn
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,245.05 rating

Confidence interval: 1,239.84 – 1,250.26

42998 votes

Nov 9, 2026

Category: non_english
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,271.70 rating

Confidence interval: 1,267.80 – 1,275.59

98114 votes

Nov 9, 2026

Category: overall
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,301.71 rating

Confidence interval: 1,245.59 – 1,357.83

178 votes

Nov 9, 2026

Category: polish
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,259.26 rating

Confidence interval: 1,250.94 – 1,267.59

9938 votes

Nov 9, 2026

Category: russian
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-11-09 · rating

GPT-4 Turbo (2024-04-09)

1,259.79 rating

Confidence interval: 1,238.58 – 1,281.00

1430 votes

Nov 9, 2026

Category: spanish
Evaluated configuration: GPT-4 Turbo (2024-04-09)
Evaluation type: human preference

Run it locally

Inference · memory estimate

GPT-4 Turbo (2024-04-09)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary