The AI arena is free today

Open Superagent

Llama 3.2 90B Instruct vs MiMo-V2.6-Pro

MiMo-V2.6-Pro leads the LLM Stats Score 49.8 to 5.2. Llama 3.2 90B Instruct is 1.5x cheaper per token.

Meta · Xiaomi · Updated for 2026

Which is better?

MiMo-V2.6-Pro leads the overall LLM Stats Score 49.8 to 5.2, ranking #19 overall.

On price, Llama 3.2 90B Instruct is roughly 1.5x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

MiMo-V2.6-Pro also accepts a larger context window (1,048,576 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Llama 3.2 90B Instruct

  • cost matters — it's about 1.5x cheaper per token

Choose MiMo-V2.6-Pro

  • overall performance matters — it scores 49.8 and ranks #19 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you process long inputs — it offers a 1,048,576 token context window
  • you want the most recent training data — it shipped Sep 2026

At a glance

The differences that matter most.

Core performance indexes
5.2
#300
49.8
#19
6.7
#288
45.2
#30
Cost, coverage & limits
Benchmark wins
Input price
$0.35 / M
$0.43 / M
Output price
$0.40 / M
$0.87 / M
Context window
128,000
1,048,576

Individual benchmarks

13 reported for Llama 3.2 90B Instruct · 18 for MiMo-V2.6-Pro

No common benchmarks found

Llama 3.2 90B Instruct and MiMo-V2.6-Prodon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Llama 3.2 90B Instruct costs less

For input processing, Llama 3.2 90B Instruct ($0.35/1M tokens) is 1.2x cheaper than MiMo-V2.6-Pro ($0.43/1M tokens).

For output processing, Llama 3.2 90B Instruct ($0.40/1M tokens) is 2.2x cheaper than MiMo-V2.6-Pro ($0.87/1M tokens).

In conclusion, MiMo-V2.6-Pro is more expensive than Llama 3.2 90B Instruct.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Tue Sep 22 2026 • llm-stats.com
Meta
Llama 3.2 90B Instruct
Input tokens$0.35
Output tokens$0.40
Best providerDeepinfra
Xiaomi
MiMo-V2.6-Pro
Input tokens$0.43
Output tokens$0.87
Best providerXiaomi
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

930.0B diff

MiMo-V2.6-Pro has 930.0B more parameters than Llama 3.2 90B Instruct, making it 1033.3% larger.

Meta
Llama 3.2 90B Instruct
90.0Bparameters
Xiaomi
MiMo-V2.6-Pro
1.0Tparameters
90.0B
Llama 3.2 90B Instruct
1020.0B
MiMo-V2.6-Pro

Context Window

Maximum input and output token capacity

MiMo-V2.6-Pro accepts 1,048,576 input tokens compared to Llama 3.2 90B Instruct's 128,000 tokens. Only Llama 3.2 90B Instruct specifies output context (128,000 tokens).

Meta
Llama 3.2 90B Instruct
Input128,000 tokens
Output128,000 tokens
Xiaomi
MiMo-V2.6-Pro
Input1,048,576 tokens
Output- tokens
Tue Sep 22 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Llama 3.2 90B Instruct and MiMo-V2.6-Pro support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Llama 3.2 90B Instruct

Text
Images
Audio
Video

MiMo-V2.6-Pro

Text
Images
Audio
Video

License

Usage and distribution terms

Llama 3.2 90B Instruct is licensed under Llama 3.2, while MiMo-V2.6-Pro uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

Llama 3.2 90B Instruct

Llama 3.2

Open weights

MiMo-V2.6-Pro

MIT

Open weights

Release Timeline

When each model was launched

Llama 3.2 90B Instruct was released on 2024-09-25, while MiMo-V2.6-Pro was released on 2026-09-22.

MiMo-V2.6-Pro is 24 months newer than Llama 3.2 90B Instruct.

Llama 3.2 90B Instruct

Sep 25, 2024

2.0 years ago

MiMo-V2.6-Pro

Sep 22, 2026

0 days ago

2.0yr newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Llama 3.2 90B Instruct is available from DeepInfra, Bedrock, Fireworks, Together, Hyperbolic. MiMo-V2.6-Pro is available from Xiaomi.

Llama 3.2 90B Instruct

deepinfra logo
Deepinfra
Input Price:Input: $0.35/1MOutput Price:Output: $0.40/1M
bedrock logo
AWS Bedrock
Input Price:Input: $0.72/1MOutput Price:Output: $0.72/1M
fireworks logo
Fireworks
Input Price:Input: $0.89/1MOutput Price:Output: $0.89/1M
together logo
Together
Input Price:Input: $1.20/1MOutput Price:Output: $1.20/1M
hyperbolic logo
Hyperbolic
Input Price:Input: $2.00/1MOutput Price:Output: $2.00/1M

MiMo-V2.6-Pro

xiaomi logo
Xiaomi
Input Price:Input: $0.43/1MOutput Price:Output: $0.87/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Llama 3.2 90B Instruct and MiMo-V2.6-Pro side-by-side, then vote on the output you prefer.

Llama 3.2 90B Instruct
✓ Preferred
MiMo-V2.6-Pro
Open in Playground

FAQ

Common questions about Llama 3.2 90B Instruct vs MiMo-V2.6-Pro.

Which is better, Llama 3.2 90B Instruct or MiMo-V2.6-Pro?

MiMo-V2.6-Pro leads the LLM Stats Score 49.8 to 5.2. Llama 3.2 90B Instruct is made by Meta and MiMo-V2.6-Pro is made by Xiaomi. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Llama 3.2 90B Instruct compare to MiMo-V2.6-Pro in benchmarks?

Llama 3.2 90B Instruct scores AI2D: 92.3%, DocVQA: 90.1%, MGSM: 86.9%, MMLU: 86.0%, ChartQA: 85.5%. MiMo-V2.6-Pro scores CyberGym: 94.0%, Terminal-Bench 2.1: 89.9%, OSWorld-Verified: 82.0%, MiMo Cyber Bench: 81.7%, Toolathlon-Verified: 76.9%.

Is Llama 3.2 90B Instruct cheaper than MiMo-V2.6-Pro?

Llama 3.2 90B Instruct is 1.2x cheaper for input tokens. Llama 3.2 90B Instruct costs $0.35/M input and $0.40/M output via deepinfra. MiMo-V2.6-Pro costs $0.43/M input and $0.87/M output via xiaomi.

What are the context window sizes for Llama 3.2 90B Instruct and MiMo-V2.6-Pro?

Llama 3.2 90B Instruct supports 128K tokens and MiMo-V2.6-Pro supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Llama 3.2 90B Instruct and MiMo-V2.6-Pro?

Key differences include LLM Stats Score (5.2 vs 49.8), context window (128K vs 1.0M), input pricing ($0.35 vs $0.43/M), licensing (Llama 3.2 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Llama 3.2 90B Instruct and MiMo-V2.6-Pro?

Llama 3.2 90B Instruct is developed by Meta and MiMo-V2.6-Pro is developed by Xiaomi.