GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-5.2 Chat (20260210)

Model evaluation

Capability & preference

Human preference · Arena

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

GPT-5.2 Chat (20260210) 1438.5 GPT-5.2 Chat (20260210) · 95% interval 1434.5–1442.5 · 35,974 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

GPT-5.2 Chat (20260210)

1,459.63 rating

Confidence interval: 1,447.30 – 1,471.96

2399 votes

Oct 28, 2026

Category: chinese
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,446.37 rating

Confidence interval: 1,439.67 – 1,453.07

9621 votes

Oct 28, 2026

Category: coding
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,400.90 rating

Confidence interval: 1,392.54 – 1,409.27

5632 votes

Oct 28, 2026

Category: creative_writing
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,445.93 rating

Confidence interval: 1,440.43 – 1,451.44

15902 votes

Oct 28, 2026

Category: english
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,432.59 rating

Confidence interval: 1,427.35 – 1,437.83

27303 votes

Oct 28, 2026

Category: exclude_ties
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,437.84 rating

Confidence interval: 1,427.04 – 1,448.63

3159 votes

Oct 28, 2026

Category: expert
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,437.94 rating

Confidence interval: 1,418.31 – 1,457.57

1043 votes

Oct 28, 2026

Category: french
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,447.58 rating

Confidence interval: 1,422.43 – 1,472.72

562 votes

Oct 28, 2026

Category: german
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,445.01 rating

Confidence interval: 1,440.11 – 1,449.91

22844 votes

Oct 28, 2026

Category: hard_prompts
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,450.67 rating

Confidence interval: 1,444.16 – 1,457.17

10395 votes

Oct 28, 2026

Category: hard_prompts_english
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,432.72 rating

Confidence interval: 1,425.15 – 1,440.28

7011 votes

Oct 28, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,399.53 rating

Confidence interval: 1,391.98 – 1,407.08

7103 votes

Oct 28, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,435.96 rating

Confidence interval: 1,424.19 – 1,447.73

2707 votes

Oct 28, 2026

Category: industry_legal_and_government
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,438.43 rating

Confidence interval: 1,430.33 – 1,446.52

5817 votes

Oct 28, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,430.41 rating

Confidence interval: 1,416.79 – 1,444.04

2012 votes

Oct 28, 2026

Category: industry_mathematical
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,441.39 rating

Confidence interval: 1,429.38 – 1,453.40

2601 votes

Oct 28, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,454.01 rating

Confidence interval: 1,448.23 – 1,459.79

14031 votes

Oct 28, 2026

Category: industry_software_and_it_services
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,421.92 rating

Confidence interval: 1,414.98 – 1,428.86

8489 votes

Oct 28, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,416.85 rating

Confidence interval: 1,410.67 – 1,423.03

11758 votes

Oct 28, 2026

Category: instruction_following
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,417.76 rating

Confidence interval: 1,381.85 – 1,453.68

267 votes

Oct 28, 2026

Category: japanese
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,392.09 rating

Confidence interval: 1,366.16 – 1,418.01

554 votes

Oct 28, 2026

Category: korean
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,427.46 rating

Confidence interval: 1,421.51 – 1,433.42

13951 votes

Oct 28, 2026

Category: longer_query
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,434.68 rating

Confidence interval: 1,421.70 – 1,447.66

2171 votes

Oct 28, 2026

Category: math
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,457.75 rating

Confidence interval: 1,450.01 – 1,465.50

6798 votes

Oct 28, 2026

Category: multi_turn
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,425.01 rating

Confidence interval: 1,420.00 – 1,430.01

20072 votes

Oct 28, 2026

Category: non_english
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,438.50 rating

Confidence interval: 1,434.50 – 1,442.49

35974 votes

Oct 28, 2026

Category: overall
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,433.18 rating

Confidence interval: 1,411.15 – 1,455.21

708 votes

Oct 28, 2026

Category: polish
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,439.90 rating

Confidence interval: 1,430.67 – 1,449.13

4431 votes

Oct 28, 2026

Category: russian
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

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

GPT-5.2 Chat (20260210)

1,432.61 rating

Confidence interval: 1,414.88 – 1,450.33

1206 votes

Oct 28, 2026

Category: spanish
Evaluated configuration: GPT-5.2 Chat (20260210)
Evaluation type: human preference

Run it locally

Inference · memory estimate

GPT-5.2 Chat (20260210)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary