The AI arena is free today

Open Superagent

Pixtral Large vs QvQ-72B-Preview

Pixtral Large and QvQ-72B-Preview are closely matched at 11.8 and 7.9 on the LLM Stats Score.

Mistral AI · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Pixtral Large and QvQ-72B-Preview are closely matched on the overall LLM Stats Score at 11.8 and 7.9.

In the 2 individual benchmarks reported for both models, QvQ-72B-Preview wins 2; this is a narrower head-to-head signal than the composite indexes.

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

Choose Pixtral Large

  • you want predictable pricing at $2.00/M input and $6.00/M output

Choose QvQ-72B-Preview

  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results
  • you want the most recent training data — it shipped Dec 2024

At a glance

The differences that matter most.

Core performance indexes
11.8
#260
7.9
#286
13.1
#244
8.2
#279
Cost, coverage & limits
Benchmark wins
0 of 2
2 of 2
Input price
$2.00 / M
— / M
Output price
$6.00 / M
— / M
Context window
128,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Pixtral Large
QvQ-72B-Preview
10.9#117
6.3#150
13.4#103
9.6#121
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

7 reported for Pixtral Large · 4 for QvQ-72B-Preview

2 shared

Pixtral Large outperforms in 0 benchmarks, while QvQ-72B-Preview is better at 2 benchmarks (MathVista, MMMU).

QvQ-72B-Preview significantly outperforms across most benchmarks.

Tue Sep 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

50.6B diff

Pixtral Large has 50.6B more parameters than QvQ-72B-Preview, making it 68.9% larger.

Mistral AI
Pixtral Large
124.0Bparameters
Alibaba Cloud / Qwen Team
QvQ-72B-Preview
73.4Bparameters
124.0B
Pixtral Large
73.4B
QvQ-72B-Preview

Context Window

Maximum input and output token capacity

Only Pixtral Large specifies input context (128,000 tokens). Only Pixtral Large specifies output context (128,000 tokens).

Mistral AI
Pixtral Large
Input128,000 tokens
Output128,000 tokens
Alibaba Cloud / Qwen Team
QvQ-72B-Preview
Input- tokens
Output- tokens
Tue Sep 22 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Pixtral Large and QvQ-72B-Preview support multimodal inputs.

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

Pixtral Large

Text
Images
Audio
Video

QvQ-72B-Preview

Text
Images
Audio
Video

License

Usage and distribution terms

Pixtral Large is licensed under Mistral Research License (MRL) for research; Mistral Commercial License for commercial use, while QvQ-72B-Preview uses Qwen.

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

Pixtral Large

Mistral Research License (MRL) for research; Mistral Commercial License for commercial use

Open weights

QvQ-72B-Preview

Qwen

Open weights

Release Timeline

When each model was launched

Pixtral Large was released on 2024-11-18, while QvQ-72B-Preview was released on 2024-12-25.

QvQ-72B-Preview is 1 month newer than Pixtral Large.

Pixtral Large

Nov 18, 2024

1.8 years ago

QvQ-72B-Preview

Dec 25, 2024

1.7 years ago

1mo 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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Pixtral Large and QvQ-72B-Preview side-by-side, then vote on the output you prefer.

Pixtral Large
✓ Preferred
QvQ-72B-Preview
Open in Playground

FAQ

Common questions about Pixtral Large vs QvQ-72B-Preview.

Which is better, Pixtral Large or QvQ-72B-Preview?

Pixtral Large and QvQ-72B-Preview are closely matched on the LLM Stats Score at 11.8 and 7.9. Pixtral Large is made by Mistral AI 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 Pixtral Large compare to QvQ-72B-Preview in benchmarks?

Pixtral Large scores AI2D: 93.8%, DocVQA: 93.3%, ChartQA: 88.1%, VQAv2: 80.9%, MM-MT-Bench: 74.0%. QvQ-72B-Preview scores MathVista: 71.4%, MMMU: 70.3%, MathVision: 35.9%, OlympiadBench: 20.4%.

What are the context window sizes for Pixtral Large and QvQ-72B-Preview?

Pixtral Large supports 128K tokens and QvQ-72B-Preview supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Pixtral Large and QvQ-72B-Preview?

Key differences include LLM Stats Score (11.8 vs 7.9), licensing (Mistral Research License (MRL) for research; Mistral Commercial License for commercial use vs Qwen). See the full comparison above for benchmark-by-benchmark results.

Who makes Pixtral Large and QvQ-72B-Preview?

Pixtral Large is developed by Mistral AI and QvQ-72B-Preview is developed by Alibaba Cloud / Qwen Team.