EXAONE Deep 32B
32B reasoning model by LG AI Research, excelling in math and code tasks with competitive open-weight performance.
Performance benchmarks
Model | AIME 2025 | GPQA Diamond | HLE | LiveCodeBench | MATH500 | SWE-bench verified |
|---|---|---|---|---|---|---|
EXAONE Deep 32B | 65.8% | 66.1% | 59.5% | 95.7% | Related open-source models | Competitor closed-source models |
 Claude Opus 4.6 | 90.5% | 34.2% | 78.7% | |||
 OpenAI o3 | 83.3% | 24.9% | 99.2% | 62.3% | ||
OpenAI o1 | 76.8% | 96.4% | 48.9% | |||
GPT-4o | 49.2% | 2.7% | 32.3% | 89.3% | 31.0% |
This model is not available on Together’s Serverless API.
Pick a supported alternative from the Model Library.
Related models
- Model providerLG AI Research
- TypeChatReasoning
- Main use casesChatReasoning
- Parameters32B
- Context length32K
- External link
- CategoryChat