Claude 3.5 Haiku vs Sonar Reasoning Pro
Anthropic vs Perplexity — benchmarks, pricing, and capabilities side by side.
- •Sonar Reasoning Pro has the higher intelligence index (95.7 vs 54.5)
- •Claude 3.5 Haiku is cheaper ($0.80 vs $2.00 per 1M input)
- •Claude 3.5 Haiku has a larger context window (200K)
| Claude 3.5 Haiku | Sonar Reasoning Pro | |
|---|---|---|
| Intelligence index | 54.5 | 95.7 |
| Developer | Anthropic | Perplexity |
| Type | LLM | Multimodal |
| Access | API only | API only |
| Context window | 200,000 tokens | 128,000 tokens |
| Input price | $0.80 / 1M | $2.00 / 1M |
| Output price | $4.00 / 1M | $8.00 / 1M |
| Speed | 104 tok/s | — |
| Released | November 4, 2024 | March 7, 2025 |
| Parameters | — | — |
| Input modalities | Text, Image | Text, Image |
| Output modalities | Text | Text |
Shared benchmarks
Claude 3.5 Haiku
Sonar Reasoning Pro
MATH-500
72.1
95.7