Claude 4 Sonnet vs GPT-5.2
GPT-5.2 is cheaper on output tokens, while GPT-5.2 offers a larger context window. Choose Claude 4 Sonnet or GPT-5.2 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Claude 4 Sonnet | GPT-5.2 |
|---|---|---|
| Provider | NanoGPT | OpenAI |
| Input / 1M tokens | $2.99 | $1.75 |
| Output / 1M tokens | $14.99 | $14.00 |
| Context window | 200K | 400K |
| Parameters | — | — |
| Open weights | No | No |
| Released | Sep 2025 | Dec 2025 |
| LiveBench score | 60.6 | 75.4 |
| SWE-bench Verified score | 76.4 | 72.8 |
| SWE-bench Multimodal score | 35.6 | — |
| SWE-bench Multilingual score | — | 66.7 |
| LMArena (Chatbot Arena) Elo score | — | 1416 |
| LMArena WebDev Elo score | — | 1417 |
| LMArena Vision Elo score | — | 1246 |
| GPQA Diamond score | — | 91.4 |
| FrontierMath score | — | 40.7 |
| Epoch Capabilities Index score | — | 153 |
FAQ
Is Claude 4 Sonnet or GPT-5.2 cheaper?
GPT-5.2 is cheaper on output tokens ($14.00 vs $14.99 per 1M).
Which has the larger context window, Claude 4 Sonnet 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.