DeepSeek-V4-Pro-0813 vs MiMo-V2.6-Pro: Specs & Benchmark Comparison
DeepSeek-V4-Pro-0813 is developed by DeepSeek, while MiMo-V2.6-Pro comes from Xiaomi. DeepSeek-V4-Pro-0813 was released in August 2026, and MiMo-V2.6-Pro followed a month later in September 2026. DeepSeek-V4-Pro-0813 is the larger model at roughly 1.6 trillion parameters, against 1.0 trillion for MiMo-V2.6-Pro.
The two models share 3 published benchmarks. MiMo-V2.6-Pro leads on 3 of them. The widest gaps are on CyberGym, where MiMo-V2.6-Pro scores 94.0% against 83.0%; Agents' Last Exam, where MiMo-V2.6-Pro scores 31.6% against 25.7%. Averaged across everything we track, DeepSeek-V4-Pro-0813 sits at 60.6% and MiMo-V2.6-Pro at 59.7%.
MiMo-V2.6-Pro is the cheaper API at $0.43 per million input tokens and $0.87 per million output tokens, roughly 3 times cheaper than DeepSeek-V4-Pro-0813 at $1.32 and $3.96. Both accept a context window of about 1M tokens. DeepSeek-V4-Pro-0813 accepts text as input, while MiMo-V2.6-Pro accepts text, images, audio, and video.
| Characteristic | DeepSeek-V4-Pro-0813 | MiMo-V2.6-Pro |
|---|---|---|
| Company | DeepSeek | Xiaomi |
| Release Date | August 13, 2026 | September 22, 2026 |
| Parameters | 1.6T | 1.0T |
| Multimodal | No | Yes |
| Context (input) | 1.0M | 1.0M |
| Context (output) | 393K | — |
| Input Price / 1M | $1.32 | $0.43 |
| Output Price / 1M | $3.96 | $0.87 |
| Average Score | 60.6% | 59.7% |
| Benchmarks | ||
| CyberGym | 83.0% | 94.0% |
| Agents' Last Exam | 25.7% | 31.6% |
| Terminal-Bench 2.1 | 88.0% | 89.9% |
Visual Benchmark Comparison
Verdict
MiMo-V2.6-Pro leads in 2 out of 4 comparison categories.
Both models show comparable average scores: DeepSeek-V4-Pro-0813 — 0.6, MiMo-V2.6-Pro — 0.6.
MiMo-V2.6-Pro is 4.0x cheaper: input $0.43/1M vs $1.32/1M tokens.
Same context size: 1M tokens.
MiMo-V2.6-Pro is newer: released 9/22/2026 vs 8/13/2026.
More About These Models
Related Comparisons
Frequently Asked Questions
Which is better for coding — DeepSeek-V4-Pro-0813 or MiMo-V2.6-Pro?
Which model is cheaper — DeepSeek-V4-Pro-0813 or MiMo-V2.6-Pro?
Which has a larger context window — DeepSeek-V4-Pro-0813 or MiMo-V2.6-Pro?
The DeepSeek-V4-Pro-0813 and MiMo-V2.6-Pro comparison is updated for 2026. Data includes benchmark results, API pricing, context window size and other specifications. For more detailed information, visit the DeepSeek-V4-Pro-0813 or MiMo-V2.6-Pro page. See also the complete list of AI model comparisons.