The AI arena is free today

Open Superagent

K-EXAONE-236B-A23B vs Qwen2-VL-72B-Instruct

K-EXAONE-236B-A23B leads the LLM Stats Score 26.3 to 14.4.

LG AI Research · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

K-EXAONE-236B-A23B leads the overall LLM Stats Score 26.3 to 14.4, ranking #149 overall.

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

Choose K-EXAONE-236B-A23B

  • overall performance matters — it scores 26.3 and ranks #149 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Dec 2025

Choose Qwen2-VL-72B-Instruct

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

K-EXAONE-236B-A23B
LG AI Research
Qwen2-VL-72B-Instruct
Alibaba Cloud / Qwen Team
Core performance indexes
LLM Stats Score
26.3
#149
14.4
#235
Reasoning
27.3
#137
11.7
#250
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.60 / M
— / M
Output price
$1.00 / M
— / M
Context window
32,768
—

Individual benchmarks

6 reported for K-EXAONE-236B-A23B · 15 for Qwen2-VL-72B-Instruct

No common benchmarks found

K-EXAONE-236B-A23B and Qwen2-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

162.6B diff

K-EXAONE-236B-A23B has 162.6B more parameters than Qwen2-VL-72B-Instruct, making it 221.5% larger.

LG AI Research
K-EXAONE-236B-A23B
236.0Bparameters
Alibaba Cloud / Qwen Team
Qwen2-VL-72B-Instruct
73.4Bparameters
236.0B
K-EXAONE-236B-A23B
73.4B
Qwen2-VL-72B-Instruct

Context Window

Maximum input and output token capacity

Only K-EXAONE-236B-A23B specifies input context (32,768 tokens). Only K-EXAONE-236B-A23B specifies output context (32,768 tokens).

LG AI Research
K-EXAONE-236B-A23B
Input32,768 tokens
Output32,768 tokens
Alibaba Cloud / Qwen Team
Qwen2-VL-72B-Instruct
Input- tokens
Output- tokens
Thu Sep 10 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Qwen2-VL-72B-Instruct supports multimodal inputs, whereas K-EXAONE-236B-A23B does not.

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

K-EXAONE-236B-A23B

Text
Images
Audio
Video

Qwen2-VL-72B-Instruct

Text
Images
Audio
Video

License

Usage and distribution terms

K-EXAONE-236B-A23B is licensed under a proprietary license, while Qwen2-VL-72B-Instruct uses tongyi-qianwen.

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

K-EXAONE-236B-A23B

Proprietary

Closed source

Qwen2-VL-72B-Instruct

tongyi-qianwen

Open weights

Release Timeline

When each model was launched

K-EXAONE-236B-A23B was released on 2025-12-31, while Qwen2-VL-72B-Instruct was released on 2024-08-29.

K-EXAONE-236B-A23B is 16 months newer than Qwen2-VL-72B-Instruct.

K-EXAONE-236B-A23B

Dec 31, 2025

8 months ago

1.3yr newer
Qwen2-VL-72B-Instruct

Aug 29, 2024

2.0 years ago

Knowledge Cutoff

When training data ends

K-EXAONE-236B-A23B has a knowledge cutoff of 2025-10-01, while Qwen2-VL-72B-Instruct has a cutoff of 2023-06-30.

K-EXAONE-236B-A23B has more recent training data (up to 2025-10-01), making it potentially better informed about events through that date compared to Qwen2-VL-72B-Instruct (2023-06-30).

K-EXAONE-236B-A23B

Oct 2025

2.3 yr newer
Qwen2-VL-72B-Instruct

Jun 2023

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against K-EXAONE-236B-A23B and Qwen2-VL-72B-Instruct side-by-side, then vote on the output you prefer.

K-EXAONE-236B-A23B
✓ Preferred
Qwen2-VL-72B-Instruct
Open in Playground

FAQ

Common questions about K-EXAONE-236B-A23B vs Qwen2-VL-72B-Instruct.

Which is better, K-EXAONE-236B-A23B or Qwen2-VL-72B-Instruct?

K-EXAONE-236B-A23B leads the LLM Stats Score 26.3 to 14.4. K-EXAONE-236B-A23B is made by LG AI Research and Qwen2-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 K-EXAONE-236B-A23B compare to Qwen2-VL-72B-Instruct in benchmarks?

K-EXAONE-236B-A23B scores AIME 2025: 92.8%, MMMLU: 85.7%, MMLU-Pro: 83.8%, LiveCodeBench v6: 80.7%, t2-bench: 73.2%. Qwen2-VL-72B-Instruct scores DocVQAtest: 96.5%, VCR_en_easy: 91.9%, ChartQA: 88.3%, OCRBench: 87.7%, MMBench: 86.5%.

What are the context window sizes for K-EXAONE-236B-A23B and Qwen2-VL-72B-Instruct?

K-EXAONE-236B-A23B supports 33K tokens and Qwen2-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 K-EXAONE-236B-A23B and Qwen2-VL-72B-Instruct?

Key differences include LLM Stats Score (26.3 vs 14.4), multimodal support (no vs yes), licensing (Proprietary vs tongyi-qianwen). See the full comparison above for benchmark-by-benchmark results.

Who makes K-EXAONE-236B-A23B and Qwen2-VL-72B-Instruct?

K-EXAONE-236B-A23B is developed by LG AI Research and Qwen2-VL-72B-Instruct is developed by Alibaba Cloud / Qwen Team.

Related comparisons