Model Comparison

Nova Lite vs Qwen2.5 VL 72B InstructWhich is better in 2026?

Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks.

Verdict: Nova Lite vs Qwen2.5 VL 72B Instruct — which is better?

Nova Lite (by Amazon) and Qwen2.5 VL 72B Instruct (by Alibaba Cloud / Qwen Team) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Nova Lite outperforms in 0 benchmarks, while Qwen2.5 VL 72B Instruct is better at 5 benchmarks (ChartQA, DocVQA, EgoSchema, LVBench, MMMU). Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks.

Choose Nova Lite if…

  • you want predictable pricing at $0.06/M input and $0.24/M output

Choose Qwen2.5 VL 72B Instruct if…

  • you want the strongest raw capability — it leads on 5 of 5 shared benchmarks
  • you want the most recent training data — it shipped Jan 2025
  • you need open weights you can self-host or fine-tune
Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

5 benchmarks

Nova Lite outperforms in 0 benchmarks, while Qwen2.5 VL 72B Instruct is better at 5 benchmarks (ChartQA, DocVQA, EgoSchema, LVBench, MMMU).

Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks.

Sun Jun 07 2026 • llm-stats.com

Arena Performance

Human preference votes

Context Window

Maximum input and output token capacity

Only Nova Lite specifies input context (300,000 tokens). Only Nova Lite specifies output context (2,048 tokens).

Amazon
Nova Lite
Input300,000 tokens
Output2,048 tokens
Alibaba Cloud / Qwen Team
Qwen2.5 VL 72B Instruct
Input- tokens
Output- tokens
Sun Jun 07 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Nova Lite and Qwen2.5 VL 72B Instruct support multimodal inputs.

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

Nova Lite

Text
Images
Audio
Video

Qwen2.5 VL 72B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

Nova Lite is licensed under a proprietary license, while Qwen2.5 VL 72B Instruct uses tongyi-qianwen.

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

Nova Lite

Proprietary

Closed source

Qwen2.5 VL 72B Instruct

tongyi-qianwen

Open weights

Release Timeline

When each model was launched

Nova Lite was released on 2024-11-20, while Qwen2.5 VL 72B Instruct was released on 2025-01-26.

Qwen2.5 VL 72B Instruct is 2 months newer than Nova Lite.

Nova Lite

Nov 20, 2024

1.5 years ago

Qwen2.5 VL 72B Instruct

Jan 26, 2025

1.4 years ago

2mo 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→

Key Takeaways

Amazon
Larger context window (300,000 tokens)
Alibaba Cloud / Qwen Team

Qwen2.5 VL 72B Instruct

View details

Alibaba Cloud / Qwen Team

Has open weights
Higher ChartQA score (89.5% vs 86.8%)
Higher DocVQA score (96.4% vs 92.4%)
Higher EgoSchema score (76.2% vs 71.4%)
Higher LVBench score (47.3% vs 40.4%)
Higher MMMU score (70.2% vs 56.2%)

Detailed Comparison

AI Model Comparison Table
Feature
Amazon
Nova Lite
Alibaba Cloud / Qwen Team
Qwen2.5 VL 72B Instruct

FAQ

Common questions about Nova Lite vs Qwen2.5 VL 72B Instruct.

Which is better, Nova Lite or Qwen2.5 VL 72B Instruct?

Qwen2.5 VL 72B Instruct significantly outperforms across most benchmarks. Nova Lite is made by Amazon and Qwen2.5 VL 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 Nova Lite compare to Qwen2.5 VL 72B Instruct in benchmarks?

Nova Lite scores GSM8k: 94.5%, ARC-C: 92.4%, DocVQA: 92.4%, IFEval: 89.7%, Translation en→Set1 COMET22: 88.8%. Qwen2.5 VL 72B Instruct scores DocVQA: 96.4%, Android Control Low_EM: 93.7%, ChartQA: 89.5%, OCRBench: 88.5%, AI2D: 88.4%.

What are the context window sizes for Nova Lite and Qwen2.5 VL 72B Instruct?

Nova Lite supports 300K tokens and Qwen2.5 VL 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 Nova Lite and Qwen2.5 VL 72B Instruct?

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

Who makes Nova Lite and Qwen2.5 VL 72B Instruct?

Nova Lite is developed by Amazon and Qwen2.5 VL 72B Instruct is developed by Alibaba Cloud / Qwen Team.

Related comparisons