K-EXAONE-236B-A23B vs QwQ-32B-Preview
K-EXAONE-236B-A23B leads the LLM Stats Score 26.1 to 9.2. QwQ-32B-Preview is 4.3x cheaper per token.
LG AI Research · Alibaba Cloud / Qwen Team · Updated for 2026
Which is better?
K-EXAONE-236B-A23B leads the overall LLM Stats Score 26.1 to 9.2, ranking #142 overall.
On price, QwQ-32B-Preview is roughly 4.3x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose K-EXAONE-236B-A23B
- overall performance matters — it scores 26.1 and ranks #142 on LLM Stats
- your work emphasizes reasoning — it leads those capability indexes
- you want the most recent training data — it shipped Dec 2025
Choose QwQ-32B-Preview
- cost matters — it's about 4.3x cheaper per token
- you need open weights you can self-host or fine-tune
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
6 reported for K-EXAONE-236B-A23B · 4 for QwQ-32B-Preview
K-EXAONE-236B-A23B and QwQ-32B-Previewdon'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
Pricing Analysis
Price comparison per million tokens
For input processing, K-EXAONE-236B-A23B ($0.60/1M tokens) is 4.0x more expensive than QwQ-32B-Preview ($0.15/1M tokens).
For output processing, K-EXAONE-236B-A23B ($1.00/1M tokens) is 5.0x more expensive than QwQ-32B-Preview ($0.20/1M tokens).
In conclusion, K-EXAONE-236B-A23B is more expensive than QwQ-32B-Preview.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
K-EXAONE-236B-A23B has 203.5B more parameters than QwQ-32B-Preview, making it 626.2% larger.
Context Window
Maximum input and output token capacity
Both models have the same input context window of 32,768 tokens. Both models can generate responses up to 32,768 tokens.
License
Usage and distribution terms
K-EXAONE-236B-A23B is licensed under a proprietary license, while QwQ-32B-Preview uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
Proprietary
Closed source
Apache 2.0
Open weights
Release Timeline
When each model was launched
K-EXAONE-236B-A23B was released on 2025-12-31, while QwQ-32B-Preview was released on 2024-11-28.
K-EXAONE-236B-A23B is 13 months newer than QwQ-32B-Preview.
Dec 31, 2025
8 months ago
1.1yr newerNov 28, 2024
1.8 years ago
Knowledge Cutoff
When training data ends
K-EXAONE-236B-A23B has a knowledge cutoff of 2025-10-01, while QwQ-32B-Preview has a cutoff of 2024-11-28.
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 QwQ-32B-Preview (2024-11-28).
Oct 2025
11 mo newerNov 2024
Provider Availability
K-EXAONE-236B-A23B is available from FriendliAI. QwQ-32B-Preview is available from DeepInfra, Hyperbolic, Fireworks, Together.
K-EXAONE-236B-A23B
QwQ-32B-Preview
Outputs Comparison
Judge for yourself.
Run your own prompts against K-EXAONE-236B-A23B and QwQ-32B-Preview side-by-side, then vote on the output you prefer.
FAQ
Common questions about K-EXAONE-236B-A23B vs QwQ-32B-Preview.