The AI arena is free today

Open Superagent

MiniMax M1 40K vs QvQ-72B-Preview

MiniMax M1 40K leads the LLM Stats Score 20.5 to 7.9.

MiniMax · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

MiniMax M1 40K leads the overall LLM Stats Score 20.5 to 7.9, ranking #194 overall.

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

Choose MiniMax M1 40K

  • overall performance matters — it scores 20.5 and ranks #194 on LLM Stats
  • you want the most recent training data — it shipped Jun 2025

Choose QvQ-72B-Preview

  • you are already invested in the Alibaba Cloud / Qwen Team ecosystem

At a glance

The differences that matter most.

Core performance indexes
20.5
#194
7.9
#282
20.7
#183
8.2
#275
Cost, coverage & limits
Benchmark wins
Input price
— / M
— / M
Output price
— / M
— / M
Context window

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
MiniMax M1 40K
QvQ-72B-Preview
18.1#187
9.6#253
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

16 reported for MiniMax M1 40K · 4 for QvQ-72B-Preview

No common benchmarks found

MiniMax M1 40K and QvQ-72B-Previewdon'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

Model Size

Parameter count comparison

382.6B diff

MiniMax M1 40K has 382.6B more parameters than QvQ-72B-Preview, making it 521.3% larger.

MiniMax
MiniMax M1 40K
456.0Bparameters
Alibaba Cloud / Qwen Team
QvQ-72B-Preview
73.4Bparameters
456.0B
MiniMax M1 40K
73.4B
QvQ-72B-Preview

Input capabilities

Documented input modalities across available providers

QvQ-72B-Preview supports multimodal inputs, whereas MiniMax M1 40K does not.

QvQ-72B-Preview can handle both text and other forms of data like images, making it suitable for multimodal applications.

MiniMax M1 40K

Text
Images
Audio
Video

QvQ-72B-Preview

Text
Images
Audio
Video

License

Usage and distribution terms

MiniMax M1 40K is licensed under MIT, while QvQ-72B-Preview uses Qwen.

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

MiniMax M1 40K

MIT

Open weights

QvQ-72B-Preview

Qwen

Open weights

Release Timeline

When each model was launched

MiniMax M1 40K was released on 2025-06-16, while QvQ-72B-Preview was released on 2024-12-25.

MiniMax M1 40K is 6 months newer than QvQ-72B-Preview.

MiniMax M1 40K

Jun 16, 2025

1.3 years ago

5mo newer
QvQ-72B-Preview

Dec 25, 2024

1.7 years ago

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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against MiniMax M1 40K and QvQ-72B-Preview side-by-side, then vote on the output you prefer.

MiniMax M1 40K
✓ Preferred
QvQ-72B-Preview
Open in Playground

FAQ

Common questions about MiniMax M1 40K vs QvQ-72B-Preview.

Which is better, MiniMax M1 40K or QvQ-72B-Preview?

MiniMax M1 40K leads the LLM Stats Score 20.5 to 7.9. MiniMax M1 40K is made by MiniMax and QvQ-72B-Preview is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does MiniMax M1 40K compare to QvQ-72B-Preview in benchmarks?

MiniMax M1 40K scores MATH-500: 96.0%, AIME 2024: 83.3%, MMLU-Pro: 80.6%, ZebraLogic: 80.1%, OpenAI-MRCR: 2 needle 128k: 76.1%. QvQ-72B-Preview scores MathVista: 71.4%, MMMU: 70.3%, MathVision: 35.9%, OlympiadBench: 20.4%.

What are the main differences between MiniMax M1 40K and QvQ-72B-Preview?

Key differences include LLM Stats Score (20.5 vs 7.9), multimodal support (no vs yes), licensing (MIT vs Qwen). See the full comparison above for benchmark-by-benchmark results.

Who makes MiniMax M1 40K and QvQ-72B-Preview?

MiniMax M1 40K is developed by MiniMax and QvQ-72B-Preview is developed by Alibaba Cloud / Qwen Team.