MiMo-V2.6-Pro Benchmarks, Pricing & Rankings
Xiaomi · 2026-08-05 · Open · Current
Snapshot 2026-10-14 · updated weekly
MiMo-V2.6-Pro ranks #32 of 42 on the AMR leaderboard.
MiMo-V2.6-Pro benchmark scores
| GPQA Diamond | 75.4% | |
| MMLU-Pro | 73.8% | |
| SWE-Bench Verified | 49.2% | |
| AIME 2025 | 72.6% | |
| LiveCodeBench v6 | 63.1% | |
| Arena Elo | 1345 |
MiMo-V2.6-Pro price, speed & context
Input price
$0.25
per 1M tokens
Output price
$1
per 1M tokens
Speed
142
tok/s
Context
256K
tokens
About MiMo-V2.6-Pro
MiMo-V2.6-Pro is Xiaomi’s open reasoning model, punching far above its parameter class on AIME-style math.
Models around MiMo-V2.6-Pro in the rankings
MiMo-V2.6-Pro FAQ
Where does MiMo-V2.6-Pro rank?
MiMo-V2.6-Pro ranks #32 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 78.0. Its strongest dimension is GPQA Diamond at 75.4%.
How much does MiMo-V2.6-Pro cost?
MiMo-V2.6-Pro costs $0.25 per million input tokens and $1 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $0.81 per million tokens.
What is the MiMo-V2.6-Pro context window?
MiMo-V2.6-Pro supports a 256K token context window and generates at a median 142 output tokens per second. That context fits roughly 171 standard documents in a single prompt.
Is MiMo-V2.6-Pro open source?
Yes — MiMo-V2.6-Pro ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than MiMo-V2.6-Pro?
GPT-5.6 Luna ranks one place higher at #31 with an AMR score of 78.4. MiMo-V2.6-Pro still wins 6 of the tracked dimensions head-to-head — check the comparison table to see exactly which.