AI Hub
← All models

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 InstructSonar Reasoning Pro
Intelligence index59.195.7
DeveloperAlibabaPerplexity
TypeLLMMultimodal
AccessOpen weightsAPI only
Context window131,072 tokens128,000 tokens
Input price$0.36 / 1M$2.00 / 1M
Output price$0.40 / 1M$8.00 / 1M
Speed100 tok/s
ReleasedSeptember 19, 2024March 7, 2025
Parameters
Input modalitiesTextText, Image
Output modalitiesTextText

Shared benchmarks

Qwen2.5 72B Instruct
Sonar Reasoning Pro
MATH-500
85.8
95.7