Model Comparison

Pixtral Large vs Qwen3 VL 235B A22B Thinking

Pixtral Large significantly outperforms across most benchmarks. Qwen3 VL 235B A22B Thinking is 2.5x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

Pixtral Large outperforms in 2 benchmarks (AI2D, MM-MT-Bench), while Qwen3 VL 235B A22B Thinking is better at 0 benchmarks.

Pixtral Large significantly outperforms across most benchmarks.

Tue May 12 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Qwen3 VL 235B A22B Thinking costs less

For input processing, Pixtral Large ($2.00/1M tokens) is 4.4x more expensive than Qwen3 VL 235B A22B Thinking ($0.45/1M tokens).

For output processing, Pixtral Large ($6.00/1M tokens) is 1.7x more expensive than Qwen3 VL 235B A22B Thinking ($3.49/1M tokens).

In conclusion, Pixtral Large is more expensive than Qwen3 VL 235B A22B Thinking.*

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

Lowest available price from all providers

Tue May 12 2026 • llm-stats.com

Pixtral Large

Input tokens$2.00

Output tokens$6.00

Best providerMistral

Qwen3 VL 235B A22B Thinking

Input tokens$0.45

Output tokens$3.49

Best providerDeepinfra

Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

112.0B diff

Qwen3 VL 235B A22B Thinking has 112.0B more parameters than Pixtral Large, making it 90.3% larger.

Pixtral Large

124.0Bparameters

Qwen3 VL 235B A22B Thinking

236.0Bparameters

124.0B

Pixtral Large

236.0B

Qwen3 VL 235B A22B Thinking

Context Window

Maximum input and output token capacity

Qwen3 VL 235B A22B Thinking accepts 262,144 input tokens compared to Pixtral Large's 128,000 tokens. Qwen3 VL 235B A22B Thinking can generate longer responses up to 262,144 tokens, while Pixtral Large is limited to 128,000 tokens.

Pixtral Large

Input128,000 tokens

Output128,000 tokens

Qwen3 VL 235B A22B Thinking

Input262,144 tokens

Output262,144 tokens

Tue May 12 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Pixtral Large and Qwen3 VL 235B A22B Thinking support multimodal inputs.

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

Pixtral Large

Text

Images

Audio

Video

Qwen3 VL 235B A22B Thinking

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 Qwen3 VL 235B A22B Thinking uses Apache 2.0.

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

Qwen3 VL 235B A22B Thinking

Apache 2.0

Open weights

Release Timeline

When each model was launched

Pixtral Large was released on 2024-11-18, while Qwen3 VL 235B A22B Thinking was released on 2025-09-22.

Qwen3 VL 235B A22B Thinking is 10 months newer than Pixtral Large.

Pixtral Large

Nov 18, 2024

1.5 years ago

Qwen3 VL 235B A22B Thinking

Sep 22, 2025

7 months ago

10mo 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

Pixtral Large is available from Mistral AI. Qwen3 VL 235B A22B Thinking is available from DeepInfra, Novita.

Pixtral Large

Mistral

Input Price:Input: $2.00/1MOutput Price:Output: $6.00/1M

Qwen3 VL 235B A22B Thinking

Deepinfra

Input Price:Input: $0.45/1MOutput Price:Output: $3.49/1M

Novita

Input Price:Input: $0.98/1MOutput Price:Output: $3.95/1M

* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Pixtral Large

View details

Mistral AI

Higher AI2D score (93.8% vs 89.2%)

Higher MM-MT-Bench score (74.0% vs 8.5%)

Qwen3 VL 235B A22B Thinking

View details

Alibaba Cloud / Qwen Team

Larger context window (262,144 tokens)

Less expensive input tokens

Less expensive output tokens

Detailed Comparison

AI Model Comparison Table
Feature	Pixtral Large	Qwen3 VL 235B A22B Thinking

FAQ

Common questions about Pixtral Large vs Qwen3 VL 235B A22B Thinking.

Which is better, Pixtral Large or Qwen3 VL 235B A22B Thinking?

Pixtral Large significantly outperforms across most benchmarks. Pixtral Large is made by Mistral AI and Qwen3 VL 235B A22B Thinking is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Pixtral Large compare to Qwen3 VL 235B A22B Thinking in benchmarks?

Pixtral Large scores AI2D: 93.8%, DocVQA: 93.3%, ChartQA: 88.1%, VQAv2: 80.9%, MM-MT-Bench: 74.0%. Qwen3 VL 235B A22B Thinking scores ZebraLogic: 97.3%, DocVQAtest: 96.5%, ScreenSpot: 95.4%, CountBench: 93.7%, MMLU-Redux: 93.7%.

Is Pixtral Large cheaper than Qwen3 VL 235B A22B Thinking?

Qwen3 VL 235B A22B Thinking is 4.4x cheaper for input tokens. Pixtral Large costs $2.00/M input and $6.00/M output via mistral. Qwen3 VL 235B A22B Thinking costs $0.45/M input and $3.49/M output via deepinfra.

What are the context window sizes for Pixtral Large and Qwen3 VL 235B A22B Thinking?

Pixtral Large supports 128K tokens and Qwen3 VL 235B A22B Thinking supports 262K 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 Qwen3 VL 235B A22B Thinking?

Key differences include context window (128K vs 262K), input pricing ($2.00 vs $0.45/M), licensing (Mistral Research License (MRL) for research; Mistral Commercial License for commercial use vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Pixtral Large and Qwen3 VL 235B A22B Thinking?

Pixtral Large is developed by Mistral AI and Qwen3 VL 235B A22B Thinking is developed by Alibaba Cloud / Qwen Team.