The AI arena is free today

Open Superagent

LongCat-Flash-Thinking-2601 vs Qwen2.5 VL 72B Instruct

LongCat-Flash-Thinking-2601 leads the LLM Stats Score 35.3 to 12.7.

Meituan · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

LongCat-Flash-Thinking-2601 leads the overall LLM Stats Score 35.3 to 12.7, ranking #89 overall.

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

Choose LongCat-Flash-Thinking-2601

  • overall performance matters — it scores 35.3 and ranks #89 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Jan 2026

Choose Qwen2.5 VL 72B Instruct

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

At a glance

The differences that matter most.

LongCat-Flash-Thinking-2601
Meituan
Qwen2.5 VL 72B Instruct
Alibaba Cloud / Qwen Team
Core performance indexes
LLM Stats Score
35.3
#89
12.7
#253
Reasoning
35.5
#84
12.8
#244
Agents
9.6
#124
4.6
#155
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.30 / M
— / M
Output price
$1.20 / M
— / M
Context window
128,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
LongCat-Flash-Thinking-2601
Qwen2.5 VL 72B Instruct
Math
30.5#74
7.6#263
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

11 reported for LongCat-Flash-Thinking-2601 · 30 for Qwen2.5 VL 72B Instruct

No common benchmarks found

LongCat-Flash-Thinking-2601 and Qwen2.5 VL 72B Instructdon'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

488.0B diff

LongCat-Flash-Thinking-2601 has 488.0B more parameters than Qwen2.5 VL 72B Instruct, making it 677.8% larger.

Meituan
LongCat-Flash-Thinking-2601
560.0Bparameters
Alibaba Cloud / Qwen Team
Qwen2.5 VL 72B Instruct
72.0Bparameters
560.0B
LongCat-Flash-Thinking-2601
72.0B
Qwen2.5 VL 72B Instruct

Context Window

Maximum input and output token capacity

Only LongCat-Flash-Thinking-2601 specifies input context (128,000 tokens). Only LongCat-Flash-Thinking-2601 specifies output context (128,000 tokens).

Meituan
LongCat-Flash-Thinking-2601
Input128,000 tokens
Output128,000 tokens
Alibaba Cloud / Qwen Team
Qwen2.5 VL 72B Instruct
Input- tokens
Output- tokens
Tue Sep 22 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Qwen2.5 VL 72B Instruct supports multimodal inputs, whereas LongCat-Flash-Thinking-2601 does not.

Qwen2.5 VL 72B Instruct can handle both text and other forms of data like images, making it suitable for multimodal applications.

LongCat-Flash-Thinking-2601

Text
Images
Audio
Video

Qwen2.5 VL 72B Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

LongCat-Flash-Thinking-2601 is licensed under MIT, 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.

LongCat-Flash-Thinking-2601

MIT

Open weights

Qwen2.5 VL 72B Instruct

tongyi-qianwen

Open weights

Release Timeline

When each model was launched

LongCat-Flash-Thinking-2601 was released on 2026-01-14, while Qwen2.5 VL 72B Instruct was released on 2025-01-26.

LongCat-Flash-Thinking-2601 is 12 months newer than Qwen2.5 VL 72B Instruct.

LongCat-Flash-Thinking-2601

Jan 14, 2026

8 months ago

11mo newer
Qwen2.5 VL 72B Instruct

Jan 26, 2025

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 LongCat-Flash-Thinking-2601 and Qwen2.5 VL 72B Instruct side-by-side, then vote on the output you prefer.

LongCat-Flash-Thinking-2601
✓ Preferred
Qwen2.5 VL 72B Instruct
Open in Playground

FAQ

Common questions about LongCat-Flash-Thinking-2601 vs Qwen2.5 VL 72B Instruct.

Which is better, LongCat-Flash-Thinking-2601 or Qwen2.5 VL 72B Instruct?

LongCat-Flash-Thinking-2601 leads the LLM Stats Score 35.3 to 12.7. LongCat-Flash-Thinking-2601 is made by Meituan and Qwen2.5 VL 72B Instruct 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 LongCat-Flash-Thinking-2601 compare to Qwen2.5 VL 72B Instruct in benchmarks?

LongCat-Flash-Thinking-2601 scores AIME 2025: 99.6%, Tau2 Telecom: 99.3%, Tau2 Retail: 88.6%, LiveCodeBench: 82.8%, GPQA: 80.5%. 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 LongCat-Flash-Thinking-2601 and Qwen2.5 VL 72B Instruct?

LongCat-Flash-Thinking-2601 supports 128K 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 LongCat-Flash-Thinking-2601 and Qwen2.5 VL 72B Instruct?

Key differences include LLM Stats Score (35.3 vs 12.7), multimodal support (no vs yes), licensing (MIT vs tongyi-qianwen). See the full comparison above for benchmark-by-benchmark results.

Who makes LongCat-Flash-Thinking-2601 and Qwen2.5 VL 72B Instruct?

LongCat-Flash-Thinking-2601 is developed by Meituan and Qwen2.5 VL 72B Instruct is developed by Alibaba Cloud / Qwen Team.

Related comparisons