GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-4.1 (2025-04-14)

Model evaluation

Capability & preference

Human preference · Arena

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

GPT-4.1 (2025-04-14) 1382.9 GPT-4.1 (2025-04-14) · 95% interval 1379.2–1386.6 · 50,281 votes · 2026-11-06

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 · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,381.73 rating

Confidence interval: 1,371.22 – 1,392.24

3314 votes

Nov 6, 2026

Category: chinese
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / codinghuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,390.50 rating

Confidence interval: 1,383.91 – 1,397.08

9241 votes

Nov 6, 2026

Category: coding
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / creative_writinghuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,363.33 rating

Confidence interval: 1,355.68 – 1,370.98

6648 votes

Nov 6, 2026

Category: creative_writing
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / englishhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,392.48 rating

Confidence interval: 1,387.67 – 1,397.29

23351 votes

Nov 6, 2026

Category: english
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,355.85 rating

Confidence interval: 1,350.83 – 1,360.87

35666 votes

Nov 6, 2026

Category: exclude_ties
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / experthuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,363.89 rating

Confidence interval: 1,352.33 – 1,375.46

2639 votes

Nov 6, 2026

Category: expert
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / frenchhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,381.57 rating

Confidence interval: 1,359.34 – 1,403.80

741 votes

Nov 6, 2026

Category: french
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / germanhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,381.04 rating

Confidence interval: 1,364.44 – 1,397.64

1284 votes

Nov 6, 2026

Category: german
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / hard_promptshuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,384.02 rating

Confidence interval: 1,379.15 – 1,388.89

22017 votes

Nov 6, 2026

Category: hard_prompts
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,393.05 rating

Confidence interval: 1,386.75 – 1,399.34

10442 votes

Nov 6, 2026

Category: hard_prompts_english
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,369.05 rating

Confidence interval: 1,362.01 – 1,376.09

8231 votes

Nov 6, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,364.69 rating

Confidence interval: 1,358.01 – 1,371.37

9016 votes

Nov 6, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,399.62 rating

Confidence interval: 1,389.05 – 1,410.19

3232 votes

Nov 6, 2026

Category: industry_legal_and_government
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,381.97 rating

Confidence interval: 1,375.08 – 1,388.87

8488 votes

Nov 6, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,359.42 rating

Confidence interval: 1,348.89 – 1,369.96

3071 votes

Nov 6, 2026

Category: industry_mathematical
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,379.70 rating

Confidence interval: 1,368.05 – 1,391.34

2771 votes

Nov 6, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,391.17 rating

Confidence interval: 1,385.80 – 1,396.55

16434 votes

Nov 6, 2026

Category: industry_software_and_it_services
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,371.05 rating

Confidence interval: 1,364.89 – 1,377.21

11329 votes

Nov 6, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,366.86 rating

Confidence interval: 1,361.14 – 1,372.58

13300 votes

Nov 6, 2026

Category: instruction_following
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / japanesehuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,318.88 rating

Confidence interval: 1,300.31 – 1,337.44

1138 votes

Nov 6, 2026

Category: japanese
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / koreanhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,338.60 rating

Confidence interval: 1,319.81 – 1,357.38

1058 votes

Nov 6, 2026

Category: korean
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / longer_queryhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,384.67 rating

Confidence interval: 1,378.31 – 1,391.03

9954 votes

Nov 6, 2026

Category: longer_query
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / mathhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,369.37 rating

Confidence interval: 1,359.15 – 1,379.59

3229 votes

Nov 6, 2026

Category: math
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / multi_turnhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,397.51 rating

Confidence interval: 1,390.66 – 1,404.36

8727 votes

Nov 6, 2026

Category: multi_turn
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / non_englishhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,369.54 rating

Confidence interval: 1,364.93 – 1,374.14

26886 votes

Nov 6, 2026

Category: non_english
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / overallhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,382.91 rating

Confidence interval: 1,379.22 – 1,386.61

50281 votes

Nov 6, 2026

Category: overall
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / polishhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,388.71 rating

Confidence interval: 1,377.14 – 1,400.27

3048 votes

Nov 6, 2026

Category: polish
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / russianhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,376.61 rating

Confidence interval: 1,367.22 – 1,386.00

3806 votes

Nov 6, 2026

Category: russian
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Arena text preference / spanishhuman preference · 2026-11-06 · rating

GPT-4.1 (2025-04-14)

1,376.19 rating

Confidence interval: 1,358.04 – 1,394.34

1131 votes

Nov 6, 2026

Category: spanish
Evaluated configuration: GPT-4.1 (2025-04-14)
Evaluation type: human preference

Run it locally

Inference · memory estimate

GPT-4.1 (2025-04-14)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary