Model Comparison

DeepSeek-V3.2 (Thinking) vs Qwen2 72B Instruct

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

2 benchmarks

DeepSeek-V3.2 (Thinking) outperforms in 2 benchmarks (GPQA, MMLU-Pro), while Qwen2 72B Instruct is better at 0 benchmarks.

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks.

Wed May 13 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

613.0B diff

DeepSeek-V3.2 (Thinking) has 613.0B more parameters than Qwen2 72B Instruct, making it 851.4% larger.

DeepSeek-V3.2 (Thinking)

685.0Bparameters

Qwen2 72B Instruct

72.0Bparameters

685.0B

DeepSeek-V3.2 (Thinking)

72.0B

Qwen2 72B Instruct

Context Window

Maximum input and output token capacity

Only DeepSeek-V3.2 (Thinking) specifies input context (131,072 tokens). Only DeepSeek-V3.2 (Thinking) specifies output context (65,536 tokens).

DeepSeek-V3.2 (Thinking)

Input131,072 tokens

Output65,536 tokens

Qwen2 72B Instruct

Input- tokens

Output- tokens

Wed May 13 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V3.2 (Thinking) is licensed under MIT, while Qwen2 72B Instruct uses tongyi-qianwen.

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

DeepSeek-V3.2 (Thinking)

MIT

Open weights

Qwen2 72B Instruct

tongyi-qianwen

Open weights

Release Timeline

When each model was launched

DeepSeek-V3.2 (Thinking) was released on 2025-12-01, while Qwen2 72B Instruct was released on 2024-07-23.

DeepSeek-V3.2 (Thinking) is 17 months newer than Qwen2 72B Instruct.

DeepSeek-V3.2 (Thinking)

Dec 1, 2025

5 months ago

1.4yr newer

Qwen2 72B Instruct

Jul 23, 2024

1.8 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→

Key Takeaways

DeepSeek-V3.2 (Thinking)

View details

DeepSeek

Larger context window (131,072 tokens)

Higher GPQA score (82.4% vs 42.4%)

Higher MMLU-Pro score (85.0% vs 64.4%)

Qwen2 72B Instruct

View details

Alibaba Cloud / Qwen Team

No standout differentiators in the data we have for this pair.

Detailed Comparison

AI Model Comparison Table
Feature	DeepSeek-V3.2 (Thinking)	Qwen2 72B Instruct

FAQ

Common questions about DeepSeek-V3.2 (Thinking) vs Qwen2 72B Instruct.

Which is better, DeepSeek-V3.2 (Thinking) or Qwen2 72B Instruct?

DeepSeek-V3.2 (Thinking) significantly outperforms across most benchmarks. DeepSeek-V3.2 (Thinking) is made by DeepSeek and Qwen2 72B Instruct 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 DeepSeek-V3.2 (Thinking) compare to Qwen2 72B Instruct in benchmarks?

DeepSeek-V3.2 (Thinking) scores AIME 2025: 93.1%, HMMT 2025: 90.2%, MMLU-Pro: 85.0%, LiveCodeBench: 83.3%, GPQA: 82.4%. Qwen2 72B Instruct scores GSM8k: 91.1%, CMMLU: 90.1%, HellaSwag: 87.6%, HumanEval: 86.0%, Winogrande: 85.1%.

What are the context window sizes for DeepSeek-V3.2 (Thinking) and Qwen2 72B Instruct?

DeepSeek-V3.2 (Thinking) supports 131K tokens and Qwen2 72B Instruct 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 DeepSeek-V3.2 (Thinking) and Qwen2 72B Instruct?

Key differences include licensing (MIT vs tongyi-qianwen). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-V3.2 (Thinking) and Qwen2 72B Instruct?

DeepSeek-V3.2 (Thinking) is developed by DeepSeek and Qwen2 72B Instruct is developed by Alibaba Cloud / Qwen Team.