GPT-3.5 Turbo (1106)
Not enough verified architecture information for a reliable VRAM estimate.
GeekRadar / The comparison desk
COMPARE.
AI modelsGPT-3.5 Turbo (1106)
Model evaluation
Capability & preference
Human preference · Arena
Overall text preferences from head-to-head votes. Not factual accuracy or a task-success rate.
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 (1106)
1,012.21 rating
Confidence interval: 987.54 – 1,036.88
708 votes
- Category
- chinese
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / codinghuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,115.53 rating
Confidence interval: 1,100.03 – 1,131.03
2121 votes
- Category
- coding
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / creative_writinghuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,034.75 rating
Confidence interval: 1,019.49 – 1,050.01
2828 votes
- Category
- creative_writing
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / englishhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,113.08 rating
Confidence interval: 1,103.47 – 1,122.68
12878 votes
- Category
- english
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / exclude_tieshuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
922.85 rating
Confidence interval: 910.68 – 935.01
11535 votes
- Category
- exclude_ties
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / experthuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,069.46 rating
Confidence interval: 1,041.45 – 1,097.46
437 votes
- Category
- expert
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / frenchhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,066.39 rating
Confidence interval: 1,027.08 – 1,105.70
310 votes
- Category
- french
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / germanhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,055.92 rating
Confidence interval: 1,020.86 – 1,090.99
325 votes
- Category
- german
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / hard_promptshuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,098.34 rating
Confidence interval: 1,085.64 – 1,111.04
3846 votes
- Category
- hard_prompts
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / hard_prompts_englishhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,114.10 rating
Confidence interval: 1,100.34 – 1,127.86
3150 votes
- Category
- hard_prompts_english
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / industry_business_and_management_and_financial_operationshuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,019.48 rating
Confidence interval: 1,000.40 – 1,038.56
1382 votes
- Category
- industry_business_and_management_and_financial_operations
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / industry_entertainment_and_sports_and_mediahuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,032.53 rating
Confidence interval: 1,017.30 – 1,047.75
2646 votes
- Category
- industry_entertainment_and_sports_and_media
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / industry_legal_and_governmenthuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,056.48 rating
Confidence interval: 1,033.72 – 1,079.23
944 votes
- Category
- industry_legal_and_government
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / industry_life_and_physical_and_social_sciencehuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,051.13 rating
Confidence interval: 1,036.17 – 1,066.10
3046 votes
- Category
- industry_life_and_physical_and_social_science
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / industry_mathematicalhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,128.41 rating
Confidence interval: 1,111.88 – 1,144.95
1746 votes
- Category
- industry_mathematical
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / industry_medicine_and_healthcarehuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,005.96 rating
Confidence interval: 983.64 – 1,028.28
906 votes
- Category
- industry_medicine_and_healthcare
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / industry_software_and_it_serviceshuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,091.14 rating
Confidence interval: 1,078.12 – 1,104.15
4128 votes
- Category
- industry_software_and_it_services
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / industry_writing_and_literature_and_languagehuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,090.88 rating
Confidence interval: 1,077.39 – 1,104.38
3932 votes
- Category
- industry_writing_and_literature_and_language
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / instruction_followinghuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,092.51 rating
Confidence interval: 1,080.40 – 1,104.61
5238 votes
- Category
- instruction_following
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / longer_queryhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,069.40 rating
Confidence interval: 1,048.60 – 1,090.20
933 votes
- Category
- longer_query
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / mathhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,141.23 rating
Confidence interval: 1,126.15 – 1,156.31
2134 votes
- Category
- math
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / multi_turnhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,077.78 rating
Confidence interval: 1,062.00 – 1,093.56
2374 votes
- Category
- multi_turn
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / non_englishhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,074.01 rating
Confidence interval: 1,060.53 – 1,087.49
3741 votes
- Category
- non_english
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / overallhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,094.08 rating
Confidence interval: 1,085.37 – 1,102.79
16619 votes
- Category
- overall
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / russianhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,077.22 rating
Confidence interval: 1,048.31 – 1,106.14
400 votes
- Category
- russian
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Arena text preference / spanishhuman preference · 2026-11-06 · rating
GPT-3.5 Turbo (1106)
1,092.69 rating
Confidence interval: 1,052.14 – 1,133.24
260 votes
- Category
- spanish
- Evaluated configuration
- GPT-3.5 Turbo (1106)
- Evaluation type
- human preference
Run it locally
Capabilities
- Model license
- Proprietary
0 selected Compare 0