Exaone 4.0 1.2B (Reasoning)
Intelligence
8.3
#493/532
Coding
3.1
#494/88
Math
50.3
#139/265
Speed
—
Pricing
—
Exaone 4.0 1.2B (Reasoning) is LG AI Research’s latest model designed for advanced reasoning tasks. It features an Intelligence Index of 8.3 and a Math Index of 50.3, making it suitable for applications requiring complex problem-solving capabilities.
When to Use Exaone 4.0 1.2B (Reasoning)
✓ Best For
- Advanced reasoning tasks
- Mathematical problem solving
- Professional data analysis
✗ Not Ideal For
- Basic coding tasks
- High-speed processing needs
How Exaone 4.0 1.2B (Reasoning) Compares
Intelligence Index · Higher is better
SarvamCohereLG AI ResearchAllen Institute for AI
Benchmark Profile
Math Index
AlibabaOpenAILG AI ResearchNVIDIADeepSeek
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (11)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 8.3 | |
| Coding Index | 3.1 | |
| Math Index | 50.3 | |
| MMLU-Pro | 588% | |
| GPQA | 515% | |
| LiveCodeBench | 516% | |
| HLE | 58% | |
| SciCode | 9.3% | |
| IFBench | 23% | |
| Tau2 | 16.4% | |
| AIME 2025 | 50.3% |
Data: Artificial Analysis · Updated: March 26, 2026
Frequently Asked Questions (15)
When was Exaone 4.0 1.2B (Reasoning) released?
Exaone 4.0 1.2B (Reasoning) was released on July 15, 2025.
Who created Exaone 4.0 1.2B (Reasoning)?
Exaone 4.0 1.2B (Reasoning) was created by LG AI Research.
How intelligent is Exaone 4.0 1.2B (Reasoning)?
Exaone 4.0 1.2B (Reasoning) scores 8 on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 8).
How verbose is Exaone 4.0 1.2B (Reasoning)?
When evaluated on the Intelligence Index, Exaone 4.0 1.2B (Reasoning) generated 29M output tokens, which is somewhat higher than average compared to other open weight models of similar size (median: 16M).
Is Exaone 4.0 1.2B (Reasoning) a reasoning model?
Yes, Exaone 4.0 1.2B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Exaone 4.0 1.2B (Reasoning) support?
Exaone 4.0 1.2B (Reasoning) supports text input.
What output modalities does Exaone 4.0 1.2B (Reasoning) support?
Exaone 4.0 1.2B (Reasoning) supports text output.
Can Exaone 4.0 1.2B (Reasoning) process images?
No, Exaone 4.0 1.2B (Reasoning) does not support image input. It can only process text.
Is Exaone 4.0 1.2B (Reasoning) multimodal?
No, Exaone 4.0 1.2B (Reasoning) is not multimodal. It only supports text input.
What is the context window of Exaone 4.0 1.2B (Reasoning)?
Exaone 4.0 1.2B (Reasoning) has a context window of 64k tokens. This determines how much text and conversation history the model can process in a single request.
Is Exaone 4.0 1.2B (Reasoning) open source?
Yes, Exaone 4.0 1.2B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does Exaone 4.0 1.2B (Reasoning) have?
Exaone 4.0 1.2B (Reasoning) has 1.28 billion parameters.
What is the license for Exaone 4.0 1.2B (Reasoning)?
Exaone 4.0 1.2B (Reasoning) is released under the EXAONE AI Model License Agreement 1.2 - NC license. Commercial use requires a separate license agreement.
How does Exaone 4.0 1.2B (Reasoning) perform on benchmarks?
Exaone 4.0 1.2B (Reasoning) achieves a score of 8 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is Exaone 4.0 1.2B (Reasoning) available via API?
Exaone 4.0 1.2B (Reasoning) is an open weights model that can be self-hosted.
