Decision support

Hy4 vs MiMo-V2.6-Pro

Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.

Models Hardware

Hy4

Tencent

Sources:models.devOpenRouter

MiMo-V2.6-Pro

Xiaomi

Sources:models.devOpenRouter

Benchmark results

Head to head on 1 benchmark both models report

Hy41lead
MiMo-V2.6-Pro0leads

Arena Text
Arena rating · Higher is better
- Hy4
  Not reported
- MiMo-V2.6-Pro
  1480
  Arena #30CI 1471 to 1490
Runs and sources
Hy4
Not reported
MiMo-V2.6-Pro
default148095% CI 1471 to 1490 · 4,066 votes
Source:Arena Text leaderboard, 2026-11-09
Arena WebDev
Arena rating · Higher is better
- Hy4
  Not reported
- MiMo-V2.6-Pro
  1624
  Arena #27CI 1617 to 1632
Runs and sources
Hy4
Not reported
MiMo-V2.6-Pro
default162495% CI 1617 to 1632 · 8,790 votes
Source:Arena WebDev leaderboard, 2026-11-10
Arena Vision
Arena rating · Higher is better
- Hy4
  Not reported
- MiMo-V2.6-Pro
  1247
  Arena #58CI 1233 to 1262
Runs and sources
Hy4
Not reported
MiMo-V2.6-Pro
default124795% CI 1233 to 1262 · 1,826 votes
Source:Arena Vision leaderboard, 2026-11-09
Agent Arena
IPS score · Higher is better
- Hy4
  Best+0.053
  +0.029 ahead · Arena #14CI +0.040 to +0.066
- MiMo-V2.6-Pro
  +0.024
  Arena #19CI +0.015 to +0.033
Runs and sources
Hy4
default+0.05395% CI +0.040 to +0.066 · 3,304,477 observations
MiMo-V2.6-Pro
default+0.02495% CI +0.015 to +0.033 · 5,764,669 observations
Source:Agent Arena leaderboard, 2026-11-11

Each model's best published result is shown; "Not reported" means no matched evaluation, not a score of zero. Arena and DeepSWE ranks are the leaderboards' own; other ranks are among catalogue models with a score. Results from different harnesses or settings are not directly comparable.

Arena ratings: Arena (lmarena-ai/leaderboard-dataset), licensed CC BY 4.0. Ratings come from pairwise human votes and are only comparable within one leaderboard; the interval is Arena's 95% confidence interval. Model names are matched to the Vertical Tabs catalog.

Model specifications

Release date

November 4, 2026

September 22, 2026

Context window

1.1M

Native context

—

Max output tokens

65,536

131,072

Knowledge cutoff

—

Open weights

Parameter count

—

528B

API pricing · USD per 1M tokens

Input

$0.417

$0.435

Output

$1.2505

$0.87

Cached input

$0.021

$0.0036

Cache write

—

Capabilities and modalities

Input modalities

text, image

text, image, video, audio

Output modalities

text

Tool calling

Supported

Reasoning option

Supported

Supported options

include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, temperature, tool_choice, tools

frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Capabilities

—

completion, thinking, tools, vision

Architecture and availability

Architecture

—

mimo_v2

Model families

—

mimo_v2

Tokenizer

Other

Instruction format

—

License

—

Providers

Provider endpoints

Ollama variants

Metadata source

ai-research

models.dev

A dash means the field is not reported. Provider-specific performance and pricing may differ.

Benchmark results

Arena Text

Arena WebDev

Arena Vision

Agent Arena

Model specifications

API pricing · USD per 1M tokens

Capabilities and modalities

Architecture and availability