49.4%
HLE (AA run)
Models / Xiaomi
MiMo · Released 2026-09-22
Xiaomi's 22 Sep 2026 open-weight MiMo-V2.6 Pro. API list $0.435 / $0.87 per 1M tokens, 1M context, 128K output. Text, image, video, and audio in; text out. No AA or Vals ledger row on this page as of 23 Sep 2026.
Current Xiaomi open-weight Pro line for long-horizon coding, multimodal input, and tool use.
Family profile
Best published score in each covered benchmark family.
3 tested benchmark families
Where MiMo-V2.6-Pro places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| AA-LCR | Long context | #2/ 184 | 86 | Artificial Analysis | 2026-09-28 |
| SciCode | Coding | #4/ 97 | 61 | Artificial Analysis | 2026-09-28 |
| Humanity's Last Exam | Reasoning | #10/ 186 | 49 | Artificial Analysis | 2026-09-28 |
| AA output speed | Performance | #127/ 219 | Artificial Analysis | 2026-11-20 |
The three highest-scoring models with pages in each capability family. Where MiMo-V2.6-Pro shows up, it's highlighted.
Benchmark rows added to the public ledger for MiMo-V2.6-Pro in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA output speed | Performance | 58 t/s | Artificial Analysis | 2 |
| AA-LCR | Long context | 86.33% | Artificial Analysis | 55 |
| Humanity's Last Exam | Reasoning | 49.4% | Artificial Analysis | 55 |
| SciCode | Coding | 60.9% | Artificial Analysis | 55 |
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.
Every catalog benchmark for MiMo-V2.6-Pro. Scores link to the original source; gaps mean no public row exists yet.
4 of 13 catalog benchmarks have a sourced row for MiMo-V2.6-Pro.
49.4%
HLE (AA run)
60.9%
SciCode (AA run)
86.33%
AA-LCR (AA run)
58 t/s
Output tokens/s (5-day average across workloads, default provider)
Permanent URL
Every format below points at version 3, published 20 Nov 2026. That URL shows exactly this record for as long as VerdictPal exists, so your reference needs no access date.
VerdictPal Editorial Desk. (2026, November 20). MiMo-V2.6-Pro: VerdictPal model page (Version 3). VerdictPal. https://verdictpal.com/models/mimo-v2-6-pro/v/3
APA 7, web page with a group author. Paste into your reference list.
Permanent URL https://verdictpal.com/models/mimo-v2-6-pro/v/3
Every answer below is assembled from the dated fields on this page. Nothing is written separately for search.
MiMo-V2.6-Pro is a Xiaomi model: Xiaomi's 22 Sep 2026 open-weight MiMo-V2.6 Pro. API list $0.435 / $0.87 per 1M tokens, 1M context, 128K output. Text, image, video, and audio in; text out. No AA or Vals ledger row on this page as of 23 Sep 2026.
Current Xiaomi open-weight Pro line for long-horizon coding, multimodal input, and tool use.
MiMo-V2.6-Pro lists $0.43 input and $0.87 output per 1M tokens. Pricing last checked 2026-09-23.
MiMo-V2.6-Pro publishes a 1M token context window.
MiMo-V2.6-Pro carries Flagship status on the model atlas.
Model alerts · Weekly digest
One email when a model lands in the atlas or gets new benchmark scores, and a Monday digest of what changed for research tools and models. Built from the same sourced data as this page.
See what changed recently →