GPT-3.5 Turbo vs GPT-5.2
GPT-3.5 Turbo is cheaper on output tokens, while GPT-5.2 offers a larger context window. Choose GPT-3.5 Turbo or GPT-5.2 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | GPT-3.5 Turbo | GPT-5.2 |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Input / 1M tokens | $0.50 | $1.75 |
| Output / 1M tokens | $1.50 | $14.00 |
| Context window | 16K | 400K |
| Parameters | 20B | — |
| Open weights | No | No |
| Released | Mar 2023 | Dec 2025 |
| LMArena (Chatbot Arena) Elo score | 1125 | 1416 |
| GPQA Diamond score | 28.0 | 91.4 |
| Epoch Capabilities Index score | 119 | 154 |
| LiveBench score | — | 75.4 |
| FrontierMath score | — | 40.7 |
| LMArena WebDev Elo score | — | 1417 |
| LMArena Vision Elo score | — | 1246 |
| SWE-bench Multilingual score | — | 66.7 |
| SWE-bench Verified score | — | 72.8 |
FAQ
Is GPT-3.5 Turbo or GPT-5.2 cheaper?
GPT-3.5 Turbo is cheaper on output tokens ($1.50 vs $14.00 per 1M).
Which has the larger context window, GPT-3.5 Turbo or GPT-5.2?
GPT-5.2 has the larger context window (400K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.