AI models
ChatGPT vs DeepSeek
ChatGPT and DeepSeek API models at the top, budget and open tiers, with benchmark scores and official prices per 1M tokens.
GPT-6.2 Astra
US$ 8.00 / US$ 40.00 prompts up to 272,000 tokensInput US$/1M / Output US$/1M · Official pricing
DeepSeek V4 Pro
US$ 1.32 / US$ 3.96 peak hoursInput US$/1M / Output US$/1M · Official pricing
GPQA Diamond
96.8% · 90.9%
GPT-6.2 Astra · DeepSeek V4 Pro
01
Direct answer
see more
02
Top tier: Pick ChatGPT if scores come first: it leads on GPQA Diamond, FrontierMath and SimpleQA Verified. Pick DeepSeek if cost matters more: at official prices it charges US$ 1.32 versus US$ 8.00 per 1M input tokens and US$ 3.96 versus US$ 40.00 per 1M output.
Mid tier: DeepSeek has no model in this tier. ChatGPT's is GPT-6.2 Sol.
Economy tier: DeepSeek has no model in this tier. ChatGPT's is GPT-6.1 Terra.
Budget tier: Pick ChatGPT if scores come first: it leads on FrontierMath and is in a statistical tie with DeepSeek V4.1 Flash on GPQA Diamond and τ-bench Verified. Pick DeepSeek if SimpleQA Verified matter more, where it leads.
Open: Pick DeepSeek: across the 2 shared benchmarks it leads on GPQA Diamond and τ-bench Verified.
Compare with
Compare with
- ChatGPT
- DeepSeek
- GPT-6.2 Astra vs Gemini 4 Carbon vs Claude Fable 5.2
- GPT-6.2 Astra vs Gemini 4 Carbon
- GPT-6.2 Astra vs Claude Fable 5.2
- GPT-6.2 Astra vs Grok 4.7
- GPT-6.1 Sol vs Gemini 3.8 Flash vs Claude Sonnet 5.5
- GPT-6 Luna vs Claude Haiku 5.5 vs DeepSeek V4.1 Flash
- ChatGPT vs Gemini
- ChatGPT vs Claude
- ChatGPT vs Grok
- ChatGPT vs Gemini vs Claude
How to read
- Each row is a ChatGPT tier: top, mid, economy and budget, from most to least expensive. «Open» sits apart and describes the weights, not the price.
- «Current model» is the one listed on OpenAI's official pricing page.
- When the current model has no published score yet, the tier's scores come from the «reference model for scores», the newest version in the line with a score.
- Prices are in US$ per 1M tokens and carry the source label: «Official lab price», «Third-party provider» or «No current price».
- Every number comes with its source and date. «No data» means no measurement exists in the open sources this section uses.
Sources
- Epoch AI, CC BY 4.0, latest version we checked.
- OpenRouter Benchmarks, CC BY 4.0, latest version we checked.
- OpenRouter, dados públicos da API; exports de benchmarks e rankings em CC BY 4.0, latest version we checked.
Dates come from the sources: OpenRouter listing or Hugging Face repo creation, which may differ from the official launch. Family and version were grouped by rule from the name.
How to cite
If you use this data, cite the page and the date you accessed it.
Adriano Meirinho. "ChatGPT vs DeepSeek". meirinho.com.br. https://meirinho.com.br/en/ia/modelos/comparar/chatgpt-vs-deepseek/. Accessed November 21, 2026.
Third-party data follows the license of each source. The full table is available as CSV and JSON.