This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
LG AI Research has launched a newer release, EXAONE 4.5 33B. We suggest considering it instead.
EXAONE 4.0 32B: Intelligence, Performance & Price Analysis
Model summary
Performance
Verbosity
EXAONE 4.0 32B (Reasoning) supports text input, outputs text, and has a 131k tokens context window.
| Input modality | Supports: text |
|---|---|
| Output modality | Supports: text |
| Context window | 131k ~197 A4 pages of size 12 Arial font |
| Total parameters | 32B |
| License | EXAONE AI Model License Agreement 1.2 - NC |
| Model weights | Hugging Face |
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
Time per Task
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Index vs. Cost per Task
Openness Index
Artificial Analysis Openness Index: Score
Cost
Cost per Intelligence Index Task
Cost to Run Artificial Analysis Intelligence Index
Pricing: Cache Hit, Input, and Output
Context Window
Context Window
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Further details
More from LG AI Research
Frequently Asked Questions
Common questions about EXAONE 4.0 32B
EXAONE 4.0 32B was released on July 15, 2025.
EXAONE 4.0 32B was created by LG AI Research.
Yes, EXAONE 4.0 32B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer. No, EXAONE 4.0 32B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
EXAONE 4.0 32B supports text input.
EXAONE 4.0 32B supports text output.
No, EXAONE 4.0 32B does not support image input. It can only process text.
No, EXAONE 4.0 32B is not multimodal. It only supports text input.
EXAONE 4.0 32B has a context window of 131k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, EXAONE 4.0 32B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
EXAONE 4.0 32B has 32B parameters.
EXAONE 4.0 32B is released under the EXAONE AI Model License Agreement 1.2 - NC license. This license does not allow commercial use. View license
EXAONE 4.0 32B is an open weights model that can be self-hosted. View providers
EXAONE 4.0 32B is an open weights model that can be downloaded and self-hosted. Compare providers
