DeepSeek V3 vs MiMo-V2.5
Both have similar output pricing, while MiMo-V2.5 offers a larger context window. Choose DeepSeek V3 or MiMo-V2.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | DeepSeek V3 | MiMo-V2.5 |
|---|---|---|
| Provider | DeepSeek | Xiaomi |
| Input / 1M tokens | $0.14 | $0.14 |
| Output / 1M tokens | $0.28 | $0.28 |
| Context window | 164K | 1.1M |
| Parameters | 671B | — |
| Open weights | Yes | Yes |
| Released | Dec 2025 | Apr 2026 |
| Epoch Capabilities Index score | 136 | — |
| SWE-bench Verified score | 42.0 | — |
| FrontierMath score | 1.7 | — |
| LMArena (Chatbot Arena) Elo score | 1375 | 1428 |
| GPQA Diamond score | 67.6 | — |
| LMArena WebDev Elo score | — | 1438 |
| LMArena Vision Elo score | — | 1247 |
FAQ
Is DeepSeek V3 or MiMo-V2.5 cheaper?
DeepSeek V3 and MiMo-V2.5 have comparable output pricing.
Which has the larger context window, DeepSeek V3 or MiMo-V2.5?
MiMo-V2.5 has the larger context window (1.1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.