EXAONE 4.0 32B vs Sonar Reasoning Pro
LG AI Research vs Perplexity — benchmarks, pricing, and capabilities side by side.
- •Sonar Reasoning Pro has the higher intelligence index (95.7 vs 79.8)
- •EXAONE 4.0 32B is cheaper ($0.00 vs $2.00 per 1M input)
| EXAONE 4.0 32B | Sonar Reasoning Pro | |
|---|---|---|
| Intelligence index | 79.8 | 95.7 |
| Developer | LG AI Research | Perplexity |
| Type | LLM | Multimodal |
| Access | — | API only |
| Context window | — | 128,000 tokens |
| Input price | $0.00 / 1M | $2.00 / 1M |
| Output price | $0.00 / 1M | $8.00 / 1M |
| Speed | — | — |
| Released | July 15, 2025 | March 7, 2025 |
| Parameters | — | — |
| Input modalities | — | Text, Image |
| Output modalities | — | Text |
Shared benchmarks
EXAONE 4.0 32B
Sonar Reasoning Pro
MATH-500
97.7
95.7