Qwen2.5 72B Instruct vs Sonar Reasoning Pro
Alibaba vs Perplexity — benchmarks, pricing, and capabilities side by side.
- •Sonar Reasoning Pro has the higher intelligence index (95.7 vs 59.1)
- •Qwen2.5 72B Instruct is cheaper ($0.36 vs $2.00 per 1M input)
- •Qwen2.5 72B Instruct has a larger context window (131K)
| Qwen2.5 72B Instruct | Sonar Reasoning Pro | |
|---|---|---|
| Intelligence index | 59.1 | 95.7 |
| Developer | Alibaba | Perplexity |
| Type | LLM | Multimodal |
| Access | Open weights | API only |
| Context window | 131,072 tokens | 128,000 tokens |
| Input price | $0.36 / 1M | $2.00 / 1M |
| Output price | $0.40 / 1M | $8.00 / 1M |
| Speed | 100 tok/s | — |
| Released | September 19, 2024 | March 7, 2025 |
| Parameters | — | — |
| Input modalities | Text | Text, Image |
| Output modalities | Text | Text |
Shared benchmarks
Qwen2.5 72B Instruct
Sonar Reasoning Pro
MATH-500
85.8
95.7