GPT-3.5 Turbo
Mar 2023
GPT-3.5 TurboCompare inon
Benchmarks of GPT-3.5 Turbo6
BenchmarkByScoreRank
Overall1
Knowledge1
Writing3
Legacy · saturated or no longer reported1
No benchmark matches
Rankingin non-thinking mode?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProthinkingOpen×8.4-28%$0.13Pass back reasoning_content+3BetterGPT-6 Lunalow×3.9-73%$0.005Function calling only with none · Chat Completions+3
CheaperDeepSeek V4.1 Flash 1017maxOpen×8.2-30%$0.26Pass back reasoning_content · Chat Completions+4
CheaperClaude Haiku 5.5max×7.9-73%$0.21Remove sampling parameters+5
CheaperMiniMax M3.1 Flashthinking×7.8-65%$0.22Complete model response must be appendedModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×8.4-28%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×8.2-30%$0.26Pass back reasoning_content · Chat Completions+4Claude Haiku 5.5max×7.9-73%$0.21Remove sampling parameters+5MiniMax M3.1 Flashthinking×7.8-65%$0.22Complete model response must be appended
GLM 5.3 FlashmaxOpen×7.6-68%$0.28Defaults to max · Self-hosted+4ModelScoreCostPer taskWhat changes
GPT-6 Lunalow×3.9-73%$0.005Function calling only with none · Chat Completions+3
Granite 4.2 3BthinkingOpen+65%-93%$0.006
Gemma 4 E4BthinkingOpen+62%-95%$0.008GPT-5.6 Lunalow×3.8-40%$0.01GPT OSS 20BhighOpen+63%-95%$0.011ModelScoreCostPer taskWhat changes
MiMo v2.6 ProthinkingOpen×8.4-28%$0.13Pass back reasoning_content+3DeepSeek V4.1 Flash 1017maxOpen×8.2-30%$0.26Pass back reasoning_content · Chat Completions+4GLM 5.3maxOpen×8.2+187%$2.01Reasoning cannot be disabled+3
Step 5 PreviewthinkingOpen×8+90%$1.03web_search not available · Chat Completions+2
Kimi K3maxOpen×7.9+700%$2.00Sampling parameters are fixed+3ModelScoreCostPer taskWhat changes
GPT-6 Astramedium×9—$1.54Monitoring can return HTTP 403+2GPT-6.1 Solmedium×8.7—$0.21Remove unsupported parameters+5GPT-6 Solmedium×7.3—$0.25GPT-5.6 Solmedium×7.2—$0.50GPT-5.5medium×6.2—$0.90Prompts with >272K input tokensGPT-5.3 Codexxhigh×5.9—$1.75 / $14DeprecatedGPT-5.6 Terramedium×5.5—$0.18Prompts with >272K input tokensGPT-6 Lunamedium×5.5—$0.017Function calling only with none · Chat Completions+3All OpenAI models →History
2 versionsFAQ
How much does GPT-3.5 Turbo cost?›
$0.50 per 1M input tokens and $1.50 per 1M output tokens.
Is GPT-3.5 Turbo free to use?›
There is no free API; the cheapest paid price is $0.50 per 1M input tokens.
How can I use GPT-3.5 Turbo?›
Through the API of OpenAI.
What is the context window of GPT-3.5 Turbo?›
16K tokens, with up to 4K output tokens.
When was GPT-3.5 Turbo released? Is there a newer version?›
Released 2023-03-01. It has been superseded by GPT-5.6 Terra.
Is GPT-3.5 Turbo open source?›
No, GPT-3.5 Turbo is a closed model available through an API. The closest open-weights option here is MiMo v2.6 Pro.
Can GPT-3.5 Turbo read images?›
No, it accepts text only.
What is GPT-3.5 Turbo?›
GPT-3.5 Turbo is a closed language model from OpenAI, released Mar 2023.
What are the best alternatives to GPT-3.5 Turbo?›
MiMo v2.6 Pro (cheaper), GPT-6 Luna (better).