Comprehensive side-by-side LLM comparison
DeepSeek-V3 0324 leads with 7.7% higher average benchmark score. DeepSeek-V3 0324 offers 188.4K more tokens in context window than Qwen2.5 72B Instruct. Qwen2.5 72B Instruct is $0.67 cheaper per million tokens. Qwen2.5 72B Instruct is available on 4 providers. Overall, DeepSeek-V3 0324 is the stronger choice for coding tasks.
DeepSeek
DeepSeek-V3-0324 represents a specific release iteration of DeepSeek-V3, developed to incorporate ongoing improvements and refinements. Built to provide enhanced stability and performance based on deployment learnings, it continues the evolution of the DeepSeek-V3 architecture with iterative enhancements.
Alibaba Cloud / Qwen Team
Qwen 2.5 72B was developed as the flagship text model in the Qwen 2.5 series, designed to provide advanced language capabilities with 72 billion parameters. Built to compete with frontier models in reasoning, coding, and general language tasks, it represents Qwen's most capable instruction-following model in this generation.
6 months newer

Qwen2.5 72B Instruct
Alibaba Cloud / Qwen Team
2024-09-19

DeepSeek-V3 0324
DeepSeek
2025-03-25
Cost per million tokens (USD)

DeepSeek-V3 0324

Qwen2.5 72B Instruct
Context window and performance specifications
Average performance across 3 common benchmarks

DeepSeek-V3 0324

Qwen2.5 72B Instruct
Available providers and their performance metrics

DeepSeek-V3 0324
Novita

Qwen2.5 72B Instruct

DeepSeek-V3 0324

Qwen2.5 72B Instruct

DeepSeek-V3 0324

Qwen2.5 72B Instruct
DeepInfra
Fireworks
Hyperbolic
Together