DeepSeek-V4-Pro vs Gemini Omni
Direct spec comparison of DeepSeek-V4-Pro (from DeepSeek) and Gemini Omni (from Google). Want a 3- or 4-way comparison? Open the multi-model tool →
 DeepSeek-V4-ProDeepSeek |  Gemini Omni | |
|---|---|---|
| Vendor | DeepSeek | |
| Family | DeepSeek | Gemini |
| Release date | 2026-04-22 | 2026-05-20 |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Parameters | 1.6T (49B active) | — |
| Modality | text | text, vision, audio, video |
| 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. | Multimodal Gemini variant introduced at Google I/O 2026 — unified text, image, audio, and video processing in a single model. |
| Links | ||
| Benchmarks | ||
| MMLU-Pro | 84.2% | — |
| GPQA-D | 82.4% | — |
| HumanEval | 95.1% | — |
| Aider | 80.1% | — |
| AIME-25 | 88.6% | — |
| LiveCB | 72.4% | — |
| MMMU | — | 82.5% |
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 / Gemini Omni details.