ChatGPT vs DeepSeek: the short answer
ChatGPT leads on coding benchmarks (GPT-6 Astra), DeepSeek has the cheapest API option (DeepSeek V4 Flash (Non-Reasoning) at $0.01/M input). Full benchmark, pricing, and capability breakdown below.
Benchmarks: ChatGPT vs DeepSeek at their best
Each bar is the best score any ChatGPT or DeepSeek model achieves on that benchmark. Only benchmarks where both brands have a score are shown.
🧠 Intelligence & Knowledge
💻 Coding
🤖 Agentic & Tools
Model releases over time
Every ChatGPT and DeepSeek model with a known release date, on one timeline — the release cadence of each brand at a glance.
Model Release Timeline
24 releasesHow ChatGPT and DeepSeek have trended
The best score each brand's frontier model reaches over time. Higher is better — this is the aggregate "ChatGPT vs DeepSeek as brands" view.
Pricing & Models
| Model | Input /M | Output /M | Context | Coding |
|---|---|---|---|---|
| GPT-6.1 Terra | $1.00 | $5.00 | 1050K | — |
| GPT-6 Astra | $5.00 | $25.00 | 1050K | 76.2 |
| GPT-6 Astra Pro | $10.00 | $50.00 | 1050K | — |
| GPT-5.6 Luna Pro | $0.10 | $0.60 | 1050K | — |
| GPT-5.6 Luna | $0.20 | $1.20 | 1050K | — |
| GPT-5.6 Terra Pro | $2.00 | $12.00 | 1050K | — |
| GPT-5.6 Terra | $2.00 | $12.00 | 1050K | — |
| GPT-5.6 Sol Pro | $4.00 | $20.00 | 1050K | — |
| Model | Input /M | Output /M | Context | Coding |
|---|---|---|---|---|
| DeepSeek V4.1 Flash | $0.04 | $0.10 | 1049K | — |
| DeepSeek V4 Flash Vision (Experimental) | $0.22 | $0.65 | 1049K | — |
| DeepSeek V4 Pro | $0.11 | $1.32 | 1049K | — |
| DeepSeek V4 Flash (Non-Reasoning) | $0.01 | $0.03 | 1049K | — |
| DeepSeek V3.2 Speciale | $0.27 | $0.40 | 164K | — |
| DeepSeek V3.2 | $0.21 | $0.31 | 164K | — |
| DeepSeek V3.2 Exp | $0.27 | $0.41 | 164K | — |
| DeepSeek V3.1 Terminus | $0.27 | $1.00 | 164K | — |
Prices are per 1M tokens, lowest available across API providers. Showing the 8 most recent models per brand.