+
+
+
+
+
+
+
+
VS
VS
VS
VS
VS
VS
Qwen2.5 72B Instruct vs Qwen3 30B A3B
Comprehensive side-by-side LLM comparison
Qwen3 30B A3B leads with 13.9% higher average benchmark score. Qwen3 30B A3B offers 116.7K more tokens in context window than Qwen2.5 72B Instruct. Both models have similar pricing. Overall, Qwen3 30B A3B is the stronger choice for coding tasks.
+
+
+
+
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.
+
+
+
+
Alibaba Cloud / Qwen Team
Qwen3 30B was created with a mixture-of-experts architecture featuring 30 billion total parameters and 3 billion active parameters. Built to provide strong capabilities with efficient inference through sparse activation, it balances performance with practical computational requirements.
7 months newer
Qwen2.5 72B Instruct
Alibaba Cloud / Qwen Team
2024-09-19
Qwen3 30B A3B
Alibaba Cloud / Qwen Team
2025-04-29
+
+
+
+
+
+
+
+
+
+
+
+
Pricing Comparison
Cost per million tokens (USD)
+
+
+
+
Qwen2.5 72B Instruct
Input:$0.35
Output:$0.40
+
+
+
+
Qwen3 30B A3B
Input:$0.10
Output:$0.30($0.35 cheaper)
Performance Metrics
Context window and performance specifications
Average performance across 4 common benchmarks
+
+
+
+
Qwen2.5 72B Instruct
Average Score:59.5%
+
+
+
+
Qwen3 30B A3B
Average Score:73.4%(+13.9%)
Provider Availability & Performance
Available providers and their performance metrics
+
+
+
+
Qwen2.5 72B Instruct
4 providers
DeepInfra
Throughput: 10 tok/s
Latency: 0.5ms
Fireworks
Throughput: 59 tok/s
Latency: 0.37ms
Hyperbolic
Throughput: 100 tok/s
Latency: 0.5ms
Together
Throughput: 47 tok/s
Latency: 0.5ms
+
+
+
+
Qwen2.5 72B Instruct
Avg Score:59.5%
Providers:4
+
+
+
+
Qwen3 30B A3B
Avg Score:73.4%(+13.9%)
Providers:3