GeekRadar / The comparison desk

COMPARE.

AI models

openai

GPT-3.5 Turbo (0125)

Model evaluation

Capability & preference

Human preference · Arena

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

GPT-3.5 Turbo (0125) 1124.9 GPT-3.5 Turbo (0125) · 95% interval 1120.2–1129.5 · 66,207 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-3.5 Turbo (0125)

1,075.40 rating

Confidence interval: 1,065.03 – 1,085.77

7558 votes

Nov 6, 2026

Category: chinese
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,136.16 rating

Confidence interval: 1,128.10 – 1,144.22

11130 votes

Nov 6, 2026

Category: coding
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,092.07 rating

Confidence interval: 1,083.29 – 1,100.84

9694 votes

Nov 6, 2026

Category: creative_writing
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,139.21 rating

Confidence interval: 1,133.65 – 1,144.78

39956 votes

Nov 6, 2026

Category: english
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

967.16 rating

Confidence interval: 960.31 – 974.01

44422 votes

Nov 6, 2026

Category: exclude_ties
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,065.32 rating

Confidence interval: 1,052.56 – 1,078.09

3207 votes

Nov 6, 2026

Category: expert
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,117.86 rating

Confidence interval: 1,094.80 – 1,140.92

1284 votes

Nov 6, 2026

Category: french
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,090.39 rating

Confidence interval: 1,073.11 – 1,107.66

1885 votes

Nov 6, 2026

Category: german
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,107.67 rating

Confidence interval: 1,101.07 – 1,114.28

18544 votes

Nov 6, 2026

Category: hard_prompts
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,121.76 rating

Confidence interval: 1,114.07 – 1,129.45

12416 votes

Nov 6, 2026

Category: hard_prompts_english
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,076.00 rating

Confidence interval: 1,066.32 – 1,085.67

6898 votes

Nov 6, 2026

Category: industry_business_and_management_and_financial_operations
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,088.48 rating

Confidence interval: 1,079.98 – 1,096.98

9653 votes

Nov 6, 2026

Category: industry_entertainment_and_sports_and_media
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,118.11 rating

Confidence interval: 1,105.47 – 1,130.74

3573 votes

Nov 6, 2026

Category: industry_legal_and_government
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,086.92 rating

Confidence interval: 1,078.43 – 1,095.40

11407 votes

Nov 6, 2026

Category: industry_life_and_physical_and_social_science
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,126.93 rating

Confidence interval: 1,117.90 – 1,135.97

7493 votes

Nov 6, 2026

Category: industry_mathematical
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,074.17 rating

Confidence interval: 1,061.47 – 1,086.88

3837 votes

Nov 6, 2026

Category: industry_medicine_and_healthcare
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,115.16 rating

Confidence interval: 1,108.17 – 1,122.16

18975 votes

Nov 6, 2026

Category: industry_software_and_it_services
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,138.91 rating

Confidence interval: 1,131.58 – 1,146.25

16149 votes

Nov 6, 2026

Category: industry_writing_and_literature_and_language
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,118.47 rating

Confidence interval: 1,112.14 – 1,124.80

23523 votes

Nov 6, 2026

Category: instruction_following
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,043.38 rating

Confidence interval: 1,021.20 – 1,065.55

965 votes

Nov 6, 2026

Category: japanese
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,018.95 rating

Confidence interval: 996.29 – 1,041.62

1184 votes

Nov 6, 2026

Category: korean
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,120.55 rating

Confidence interval: 1,111.43 – 1,129.67

6707 votes

Nov 6, 2026

Category: longer_query
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,141.74 rating

Confidence interval: 1,133.29 – 1,150.20

8626 votes

Nov 6, 2026

Category: math
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,116.73 rating

Confidence interval: 1,108.12 – 1,125.33

10274 votes

Nov 6, 2026

Category: multi_turn
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,107.54 rating

Confidence interval: 1,101.35 – 1,113.73

26251 votes

Nov 6, 2026

Category: non_english
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,124.88 rating

Confidence interval: 1,120.22 – 1,129.54

66207 votes

Nov 6, 2026

Category: overall
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,121.26 rating

Confidence interval: 1,062.12 – 1,180.39

144 votes

Nov 6, 2026

Category: polish
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,123.17 rating

Confidence interval: 1,112.92 – 1,133.41

5447 votes

Nov 6, 2026

Category: russian
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

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

GPT-3.5 Turbo (0125)

1,120.47 rating

Confidence interval: 1,095.51 – 1,145.44

895 votes

Nov 6, 2026

Category: spanish
Evaluated configuration: GPT-3.5 Turbo (0125)
Evaluation type: human preference

Run it locally

Inference · memory estimate

GPT-3.5 Turbo (0125)

Not enough verified architecture information for a reliable VRAM estimate.

Capabilities

Model license: Proprietary