Qwen2 Instruct 72B
Analysis Summary
Qwen2 Instruct 72B is Alibaba's 72-billion-parameter model from the Qwen2 generation, with an intelligence index of 6.0, GPQA of 0.371, and MMLU-Pro of 0.622. LiveCodeBench at 0.159 is limited, and there are no agentic, tool-use, or pricing benchmarks available.
For businesses, it offers reasonable general reasoning and content generation capability for a model of its size, but has been substantially outpaced by Qwen2.5 and Qwen3 family models. Without pricing data, cost planning is difficult, and the absence of agentic benchmarks limits its fit for automation workflows.
A -4 point regional penalty applies. Teams evaluating Alibaba's Qwen family should look to more recent releases for better performance. Qwen2 72B retains some value for self-hosted deployments where the open weights are the primary draw.
Assessed June 30, 2026
Editorial notes
Qwen2 Instruct 72B from Alibaba is a capable mid-tier open-weight model with reasonable MMLU-Pro scores, but has been superseded by multiple stronger Qwen generations and carries a regional accessibility penalty.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How Qwen2 Instruct 72B compares
Qwen2 Instruct 72B ranks #308 of 385 AI models we track for overall intelligence. Qwen2 Instruct 72B is currently free to use via OpenRouter.
Benchmark Scores
Intelligence
Technical
Benchmark data from Artificial Analysis and Hugging Face
How does Qwen2 Instruct 72B stack up?
Compare side-by-side with other professional models.
Model Information
| Provider | Alibaba |
| Release Date | June 7, 2024 |
| Status | Active |
Leaderboard Categories
Frequently asked questions about Qwen2 Instruct 72B
How much does Qwen2 Instruct 72B cost?
Qwen2 Instruct 72B is currently available for free via OpenRouter.
Who created Qwen2 Instruct 72B?
Qwen2 Instruct 72B is developed by Alibaba and was released on June 7, 2024.
