DeepSeek-V4-Pro vs GPT-5
Direct spec comparison of DeepSeek-V4-Pro (from DeepSeek) and GPT-5 (from OpenAI). Want a 3- or 4-way comparison? Open the multi-model tool →
 DeepSeek-V4-ProDeepSeek |  GPT-5OpenAI | |
|---|---|---|
| Vendor | DeepSeek | OpenAI |
| Family | DeepSeek | GPT |
| Release date | 2026-04-22 | 2025-08-07 |
| Context window | 1,000,000 tokens | 400,000 tokens |
| Parameters | 1.6T (49B active) | — |
| Modality | text | text, vision, audio |
| License | MIT | proprietary |
| Source | open weights | proprietary |
| Description | DeepSeek's flagship open-weight MoE. 1.6T parameters with 49B activated, 1M-token context, and a hybrid attention scheme (CSA + HCA) that delivers long-context inference at ~27% of V3.2's FLOPs. | OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026. |
| Links | ||
| Benchmarks | ||
| MMLU-Pro | 84.2% | 85.1% |
| GPQA-D | 82.4% | 87.3% |
| HumanEval | 95.1% | 95.2% |
| Aider | 80.1% | 85.4% |
| AIME-25 | 88.6% | 91.0% |
| LiveCB | 72.4% | 74.5% |
| MMMU | — | 74.1% |
More like this
Looking for a different head-to-head? Build your own comparison on the multi-model tool.
Or see all DeepSeek-V4-Pro details / GPT-5 details.