Model Comparison

K-EXAONE-236B-A23B vs Qwen3 VL 8B Thinking

K-EXAONE-236B-A23B significantly outperforms across most benchmarks. Qwen3 VL 8B Thinking is 1.1x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

K-EXAONE-236B-A23B outperforms in 3 benchmarks (AIME 2025, LiveCodeBench v6, MMLU-Pro), while Qwen3 VL 8B Thinking is better at 0 benchmarks.

K-EXAONE-236B-A23B significantly outperforms across most benchmarks.

Mon May 25 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Qwen3 VL 8B Thinking costs less

For input processing, K-EXAONE-236B-A23B ($0.60/1M tokens) is 3.3x more expensive than Qwen3 VL 8B Thinking ($0.18/1M tokens).

For output processing, K-EXAONE-236B-A23B ($1.00/1M tokens) is 2.1x cheaper than Qwen3 VL 8B Thinking ($2.09/1M tokens).

In conclusion, K-EXAONE-236B-A23B is more expensive than Qwen3 VL 8B Thinking.*

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

Lowest available price from all providers

Mon May 25 2026 • llm-stats.com

K-EXAONE-236B-A23B

Input tokens$0.60

Output tokens$1.00

Best providerFriendliAI

Qwen3 VL 8B Thinking

Input tokens$0.18

Output tokens$2.09

Best providerDeepinfra

Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

227.0B diff

K-EXAONE-236B-A23B has 227.0B more parameters than Qwen3 VL 8B Thinking, making it 2522.2% larger.

K-EXAONE-236B-A23B

236.0Bparameters

Qwen3 VL 8B Thinking

9.0Bparameters

236.0B

K-EXAONE-236B-A23B

9.0B

Qwen3 VL 8B Thinking

Context Window

Maximum input and output token capacity

Qwen3 VL 8B Thinking accepts 262,144 input tokens compared to K-EXAONE-236B-A23B's 32,768 tokens. Qwen3 VL 8B Thinking can generate longer responses up to 262,144 tokens, while K-EXAONE-236B-A23B is limited to 32,768 tokens.

K-EXAONE-236B-A23B

Input32,768 tokens

Output32,768 tokens

Qwen3 VL 8B Thinking

Input262,144 tokens

Output262,144 tokens

Mon May 25 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Qwen3 VL 8B Thinking supports multimodal inputs, whereas K-EXAONE-236B-A23B does not.

Qwen3 VL 8B Thinking 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

Qwen3 VL 8B Thinking

Text

Images

Audio

Video

License

Usage and distribution terms

K-EXAONE-236B-A23B is licensed under a proprietary license, while Qwen3 VL 8B Thinking uses Apache 2.0.

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

K-EXAONE-236B-A23B

Proprietary

Closed source

Qwen3 VL 8B Thinking

Apache 2.0

Open weights

Release Timeline

When each model was launched

K-EXAONE-236B-A23B was released on 2025-12-31, while Qwen3 VL 8B Thinking was released on 2025-09-22.

K-EXAONE-236B-A23B is 3 months newer than Qwen3 VL 8B Thinking.

K-EXAONE-236B-A23B

Dec 31, 2025

4 months ago

3mo newer

Qwen3 VL 8B Thinking

Sep 22, 2025

8 months ago

Knowledge Cutoff

When training data ends

K-EXAONE-236B-A23B has a documented knowledge cutoff of 2025-10-01, while Qwen3 VL 8B Thinking's cutoff date is not specified.

We can confirm K-EXAONE-236B-A23B's training data extends to 2025-10-01, but cannot make a direct comparison without Qwen3 VL 8B Thinking's cutoff date.

K-EXAONE-236B-A23B

Oct 2025

Qwen3 VL 8B Thinking

—

Provider Availability

K-EXAONE-236B-A23B is available from FriendliAI. Qwen3 VL 8B Thinking is available from DeepInfra.

K-EXAONE-236B-A23B

FriendliAI

Input Price:Input: $0.60/1MOutput Price:Output: $1.00/1M

Qwen3 VL 8B Thinking

Deepinfra

Input Price:Input: $0.18/1MOutput Price:Output: $2.09/1M

* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

K-EXAONE-236B-A23B

View details

LG AI Research

Less expensive output tokens

Higher AIME 2025 score (92.8% vs 80.3%)

Higher LiveCodeBench v6 score (80.7% vs 58.6%)

Higher MMLU-Pro score (83.8% vs 77.3%)

Qwen3 VL 8B Thinking

View details

Alibaba Cloud / Qwen Team

Larger context window (262,144 tokens)

Supports multimodal inputs

Less expensive input tokens

Has open weights

Detailed Comparison

AI Model Comparison Table
Feature	K-EXAONE-236B-A23B	Qwen3 VL 8B Thinking

FAQ

Common questions about K-EXAONE-236B-A23B vs Qwen3 VL 8B Thinking.

Which is better, K-EXAONE-236B-A23B or Qwen3 VL 8B Thinking?

K-EXAONE-236B-A23B significantly outperforms across most benchmarks. K-EXAONE-236B-A23B is made by LG AI Research and Qwen3 VL 8B 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 K-EXAONE-236B-A23B compare to Qwen3 VL 8B Thinking 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%. Qwen3 VL 8B Thinking scores DocVQAtest: 95.3%, ScreenSpot: 93.6%, MMLU-Redux: 88.8%, MMBench-V1.1: 87.5%, InfoVQAtest: 86.0%.

Is K-EXAONE-236B-A23B cheaper than Qwen3 VL 8B Thinking?

Qwen3 VL 8B Thinking is 3.3x cheaper for input tokens. K-EXAONE-236B-A23B costs $0.60/M input and $1.00/M output via friendli. Qwen3 VL 8B Thinking costs $0.18/M input and $2.09/M output via deepinfra.

What are the context window sizes for K-EXAONE-236B-A23B and Qwen3 VL 8B Thinking?

K-EXAONE-236B-A23B supports 33K tokens and Qwen3 VL 8B 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 K-EXAONE-236B-A23B and Qwen3 VL 8B Thinking?

Key differences include context window (33K vs 262K), input pricing ($0.60 vs $0.18/M), multimodal support (no vs yes), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes K-EXAONE-236B-A23B and Qwen3 VL 8B Thinking?

K-EXAONE-236B-A23B is developed by LG AI Research and Qwen3 VL 8B Thinking is developed by Alibaba Cloud / Qwen Team.