llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsGPT-3.5-Turbo

OpenAI model product

GPT-3.5-Turbo

The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.

Updated Aug 10, 2026. Default version: GPT-3.5 Turbo

Compare
LLMBoard score12.5GPT-3.5 Turbo
Coverage80%6 benchmark families
Context window16.4KTokens
Official input price$0.50OpenAI API

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
GPT-3.5 Turbo
Released
Mar 21, 2023
Knowledge cutoff
Sep 30, 2021
Parameters
N/A
Context window
16.4K
Max output
4.1K
Inputs
text
Outputs
text
Open weights
No
License
Proprietary

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

GPT-3.5 Turbo category scores

Benchmark results

Published benchmark records for the scored version GPT-3.5 Turbo.

8 rows
Columns

Show columns

DROP0.7213031.0%BAug 7, 2026
MGSM0.6283110.0%BAug 7, 2026
MathVista0.039390.0%BAug 7, 2026
MMMU0.063630.0%BAug 7, 2026
MATH0.4647110.0%BAug 7, 2026
HumanEval0.7657614.7%BAug 7, 2026
MMLU0.78310017.2%BAug 7, 2026
GPQA0.32212335.2%BAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

58 rows
Columns

Show columns

text style controlpolish2101226.1144N/AAug 6, 2026
textpolish2131120.0144N/AAug 6, 2026
text style controljapanese2211142.0965N/AAug 6, 2026
textjapanese2271043.8965N/AAug 6, 2026
text style controlkorean2371153.21,184N/AAug 6, 2026
text style controlspanish2371227.3895N/AAug 6, 2026
text style controlfrench2401230.21,284N/AAug 6, 2026
textkorean2441018.91,184N/AAug 6, 2026
textfrench2471116.51,284N/AAug 6, 2026
textspanish2501119.8895N/AAug 6, 2026
text style controlgerman2541196.81,885N/AAug 6, 2026
textgerman2621090.31,885N/AAug 6, 2026
text style controlindustry writing and literature and language2931224.416,149N/AAug 6, 2026
text style controlindustry entertainment and sports and media2941196.49,653N/AAug 6, 2026
text style controlcoding2951274.411,130N/AAug 6, 2026
text style controlrussian2951218.35,447N/AAug 6, 2026
text style controlindustry legal and government2971248.73,573N/AAug 6, 2026
text style controlindustry medicine and healthcare2971227.13,837N/AAug 6, 2026
text style controlnon english2971207.526,251N/AAug 6, 2026
text style controlinstruction following2981214.023,523N/AAug 6, 2026
text style controlmulti turn3001200.110,274N/AAug 6, 2026
text style controlchinese3011209.47,558N/AAug 6, 2026
text style controlexpert3011194.83,207N/AAug 6, 2026
text style controlmath3011200.58,626N/AAug 6, 2026
textrussian3021122.45,447N/AAug 6, 2026
text style controloverall3041224.666,207N/AAug 6, 2026
text style controlcreative writing3041189.69,694N/AAug 6, 2026
text style controlindustry mathematical3051197.47,493N/AAug 6, 2026
text style controlindustry software and it services3051245.318,975N/AAug 6, 2026
text style controllonger query3051220.56,707N/AAug 6, 2026
text style controlexclude ties3061110.544,422N/AAug 6, 2026
text style controlhard prompts3071228.018,544N/AAug 6, 2026
textexpert3091064.73,207N/AAug 6, 2026
text style controlhard prompts english3091239.812,416N/AAug 6, 2026
text style controlindustry business and management and financial operations3101198.96,898N/AAug 6, 2026
textmath3111141.88,626N/AAug 6, 2026
textnon english3111107.526,251N/AAug 6, 2026
text style controlindustry life and physical and social science3111223.111,407N/AAug 6, 2026
textindustry legal and government3121118.03,573N/AAug 6, 2026
textindustry medicine and healthcare3121073.53,837N/AAug 6, 2026
textinstruction following3121119.023,523N/AAug 6, 2026
textindustry writing and literature and language3131139.016,149N/AAug 6, 2026
text style controlenglish3131236.939,956N/AAug 6, 2026
textchinese3141074.47,558N/AAug 6, 2026
textcoding3141136.911,130N/AAug 6, 2026
textindustry mathematical3141126.87,493N/AAug 6, 2026
textmulti turn3141116.810,274N/AAug 6, 2026
textlonger query3161121.16,707N/AAug 6, 2026
textexclude ties322967.844,422N/AAug 6, 2026
texthard prompts3221108.218,544N/AAug 6, 2026
textindustry entertainment and sports and media3221089.19,653N/AAug 6, 2026
textoverall3231125.166,207N/AAug 6, 2026
textindustry software and it services3231116.318,975N/AAug 6, 2026
texthard prompts english3241123.712,416N/AAug 6, 2026
textindustry business and management and financial operations3271075.96,898N/AAug 6, 2026
textcreative writing3311092.79,694N/AAug 6, 2026
textenglish3311139.439,956N/AAug 6, 2026
textindustry life and physical and social science3331087.411,407N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
$0.50 input, $1.5 output per 1M
Official provider
OpenAI
Lowest third-party
From $0.50 input, $1.5 output per 1M via Azure Cognitive Services
Tracked offerings
3
3 rows
Columns

Show columns

Azure Cognitive Servicesgpt-3.5-turbo-0125global$0.50$1.516.4KAug 7, 2026
Azuregpt-3.5-turbo-0125global$0.50$1.516.4KAug 7, 2026
OpenAIgpt-3.5-turboglobal$0.50$1.516.4KAug 7, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

GPT-3.5-Turbo versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

GPT-3.5 TurboMar 21, 202312.5N/A16.4K4.1KNoProprietary

What is GPT-3.5-Turbo?

A concise description based on the published model registry.

The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

GPT-3.5-Turbo vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

GPT-3.5-TurbovsQwen2 7BGPT-3.5-TurbovsGemma 4 E2BGPT-3.5-TurbovsQwen3 VL 8BGPT-3.5-TurbovsGPT-4.1-nanoGPT-3.5-TurbovsGemma 3n E2B LiteRTGPT-3.5-TurbovsERNIE 4.5

Models similar to GPT-3.5-Turbo

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#164-1.1
OP

GPT-4.1-nano

OpenAI

11.4 LLMBoard

DetailsCompare
#149+10.1
OP

GPT-4.1-mini

OpenAI

22.5 LLMBoard

DetailsCompare
#141+15.4
OP

GPT-4o

OpenAI

27.9 LLMBoard

DetailsCompare
#139+16.0
OP

GPT-4.1

OpenAI

28.4 LLMBoard

DetailsCompare
#138+16.1
OP

GPT-4

OpenAI

28.5 LLMBoard

DetailsCompare
#109+29.0
OP

GPT-4o-mini

OpenAI

41.5 LLMBoard

DetailsCompare

FAQ

Common questions about GPT-3.5-Turbo.

When was GPT-3.5-Turbo released?

GPT-3.5-Turbo's default version was released on Mar 21, 2023.

How much does GPT-3.5-Turbo cost?

GPT-3.5-Turbo's official API price is $0.50 per million input tokens and $1.5 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.50 input and $1.5 output via Azure Cognitive Services.

Who created GPT-3.5-Turbo?

GPT-3.5-Turbo is published under OpenAI in the model registry.

What is the context window for GPT-3.5-Turbo?

The default version has a 16.4K token context window.

Is GPT-3.5-Turbo open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer GPT-3.5-Turbo?

3 published provider offerings are linked to the default version.

What models should I compare GPT-3.5-Turbo with?

Nearby ranked alternatives include Qwen2 7B, Gemma 4 E2B, Qwen3 VL 8B.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai