MiMo-V2.5-Pro vs MiMo-V2.6-Pro
| Spec | MiMo-V2.5-Pro | MiMo-V2.6-Pro |
|---|---|---|
| Respan Index | 30.2 (#90) | 55.9 (#25) |
| Blended price per 1M | $0.81 | $0.486 |
| Context window | - | 1M |
| Input / output per 1M | $0.48 / $1.8 | $0.387 / $0.783 |
| Max output | - | - |
| Input | text | text, vision, audio, video |
| Released | - | 2026-09-21 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | MiMo-V2.5-Pro | MiMo-V2.6-Pro |
|---|---|---|
| Coding | 5.9 MiMo-V2.5-Pro | 45.9 MiMo-V2.6-Pro |
| Agents | 50.2 MiMo-V2.5-Pro | 64.5 MiMo-V2.6-Pro |
| Reasoning | 24.8* MiMo-V2.5-Pro | 55.6 MiMo-V2.6-Pro |
| Knowledge & language | 19.8* MiMo-V2.5-Pro | 58.8* MiMo-V2.6-Pro |
| Human preference | 53.1 MiMo-V2.5-Pro | 56.6 MiMo-V2.6-Pro |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
MiMo-V2.6-Pro leads on 4 of the 4 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | MiMo-V2.5-Pro | MiMo-V2.6-Pro |
|---|---|---|
| LMArena Elo | 1466 | 1481 |
| LMArena WebDev (LMArena) | 1479 | 1622 |
| LMArena Agent (LMArena) | -0.0903 | 0.0142 |
| Terminal-Bench 4.0 (Vals AI) | 0.5% | 31.3% |
FAQ
Is MiMo-V2.5-Pro better than MiMo-V2.6-Pro?
MiMo-V2.6-Pro scores 55.9 on the Respan Index (#25), ahead of MiMo-V2.5-Pro at 30.2 (#90). MiMo-V2.6-Pro leads on 4 of the 4 benchmarks both report.
Which is cheaper, MiMo-V2.5-Pro or MiMo-V2.6-Pro?
MiMo-V2.5-Pro lists at $0.48 input and $1.8 output per 1M tokens; MiMo-V2.6-Pro at $0.387 and $0.783. MiMo-V2.6-Pro is 1.7x cheaper per token at list price.