GPT-3.5 Turbo 0125
GPT-3.5 Turbo 0125Compare inon
Benchmarks of GPT-3.5 Turbo 012518
BenchmarkByScoreRank
Knowledge14
Math2
Legacy · saturated or no longer reported2
No benchmark matches
Ranking?
Retired models are left out of the current rankings.
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperMiMo v2.6 ProunstatedOpenwins 93%-28%$0.43 / $0.87Pass back reasoning_content+3BetterGPT-5 Minihighwins 86%-8%$0.053
OpenGLM 5.3maxwins 93%+187%$2.01Reasoning cannot be disabled+3CheaperGLM 5.3 FlashunstatedOpenwins 93%-68%$0.15 / $0.50Defaults to max · Self-hosted+4CheaperMiMo v2.6 FlashunstatedOpenwins 93%-77%$0.14 / $0.28Pass back reasoning_content+3ModelScoreCostPer taskWhat changes
MiMo v2.6 ProunstatedOpenwins 93%-28%$0.43 / $0.87Pass back reasoning_content+3GLM 5.3 FlashunstatedOpenwins 93%-68%$0.15 / $0.50Defaults to max · Self-hosted+4MiMo v2.6 FlashunstatedOpenwins 93%-77%$0.14 / $0.28Pass back reasoning_content+3
Qwen3.7 Plusunstatedwins 92%-25%$0.32 / $1.28MiMo v2.5 ProunstatedOpenwins 92%-28%$0.43 / $0.87ModelScoreCostPer taskWhat changes
GPT-5 Minihighwins 86%-8%$0.053GPT-6 Lunamaxwins 88%-73%$0.068Function calling only with none · Chat Completions+3GPT-5.6 Lunaxhighwins 91%-40%$0.085GPT-5.6 Terraxhighwins 93%+500%$0.63Prompts with >272K input tokensGPT-6.1 Solmaxwins 92%+433%$0.72Remove unsupported parameters+5ModelScoreCostPer taskWhat changes
GLM 5.3maxOpenwins 93%+187%$2.01Reasoning cannot be disabled+3
Kimi K3maxOpenwins 93%+700%$2.00Sampling parameters are fixed+3MiMo v2.6 ProunstatedOpenwins 93%-28%$0.43 / $0.87Pass back reasoning_content+3GLM 5.3 FlashunstatedOpenwins 93%-68%$0.15 / $0.50Defaults to max · Self-hosted+4Kimi K2.6unstatedOpenwins 93%+128%$0.95 / $4ModelScoreCostPer taskWhat changes
GPT-5.5unstatedwins 93%—$5 / $30Prompts with >272K input tokensGPT-5.6 Solxhighwins 93%—$1.18GPT-5.4highwins 93%—$2.50 / $15GPT-5.6 Terraxhighwins 93%—$0.63Prompts with >272K input tokensGPT-5.1highwins 92%—$1.25 / $10GPT-6.1 Solmaxwins 92%—$0.72Remove unsupported parameters+5GPT-6 Astramaxwins 92%—$3.26Monitoring can return HTTP 403+2GPT-5.6 Lunaxhighwins 91%—$0.085All OpenAI models →Benchmarks
all categoriesChat & Knowledge
Arena Text · Chinese1,075.3
Arena Text · English1,139.1
Arena Text · French1,117.8
Arena Text · German1,090.4
Arena Text · Japanese1,043.3
Arena Text · Korean1,018.8
Arena Text · non-English1,107.7
Arena Text · Polish1,121.3
Arena Text · Russian1,123.2
Arena Text · Spanish1,120.4
MATH Level 511.6
Writing & Language
FAQ
How much does GPT-3.5 Turbo 0125 cost?›
$0.50 per 1M input tokens and $1.50 per 1M output tokens (cheapest host: Azure Cognitive Services).
Is GPT-3.5 Turbo 0125 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 0125?›
Through the OpenAI API.
What is the context window of GPT-3.5 Turbo 0125?›
16K tokens.
When was GPT-3.5 Turbo 0125 released? Is there a newer version?›
It has been superseded by GPT-5.6 Terra.
Can GPT-3.5 Turbo 0125 read images?›
No, it accepts text only.
What is GPT-3.5 Turbo 0125?›
GPT-3.5 Turbo 0125 is a language model from OpenAI.
What are the best alternatives to GPT-3.5 Turbo 0125?›
MiMo v2.6 Pro (cheaper), GPT-5 Mini (better), GLM 5.3 (open weights).