Qwen2 Instruct 72B

Qwen2 Instruct 72B

Alibaba · Released Jun 7, 2024
Intelligence #716 / 756
9.4 our score
AA Index #355 / 435
1.0 Artificial Analysis
Input Price
Not priced
Output Price
Not priced
Context
Not reported

Analysis Summary

Qwen2 Instruct 72B is an Alibaba model released in 2024, with supplied scores for reasoning, general knowledge, coding, and scientific coding. Its MMLU Pro result is stronger than its coding measures, pointing to broad text capability but limited technical depth.

The model may work for experimentation, internal drafting, or self-hosted workloads where an open model is preferred. It is less suitable for autonomous agents, complex code changes, or high-stakes client content because the benchmark profile is modest and no tool-use, context, pricing, or modality information is available. A newer Qwen generation would be a more credible starting point where deployment flexibility is required.

Assessed September 7, 2026

Editorial notes

Qwen2 Instruct 72B provides broad benchmark coverage and useful general language capability, but its older release and limited coding results make it unsuitable for demanding modern agent or engineering workflows.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

DFO Verdict

Qwen2 Instruct 72B provides broad benchmark coverage and useful general language capability, but its older release and limited coding results make it unsuitable for demanding modern agent or engineering workflows.

#716 of 756 overall Down 63 this week

Benchmark scores

GPQA Diamond 37.1%
HLE 3.7%
MMLU Pro 62.2%
MATH 500 70.1%
AIME 14.7%
SciCode 22.9%
LiveCodeBench 15.9%

Magenta = intelligence · Ink = technical/agentic · Cyan = content & long-context · Grey = community benchmarks. Data: Artificial Analysis, Hugging Face.

1 Intelligence Index

How Qwen2 Instruct 72B compares

Qwen2 Instruct 72B ranks #355 of 435 AI models we track for overall intelligence. Qwen2 Instruct 72B is currently free to use via OpenRouter.

Position in the field
Intelligence: smarter than 5% of models #716
worst in fieldmedianbest in field
Price vs frontier peers · $ per 1M tokens
Qwen2 Instruct 72B $0.00 in $0.00 out
OpenAI: GPT-6 Astra $10.00 in $50.00 out
Anthropic: Claude Fable 5.1 $10.00 in $50.00 out
Claude Opus 5 $5.00 in $25.00 out

Dark bar = input · light bar = output, scaled to the priciest peer.

Context window vs peers · tokens

1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.

Intelligence1.1Technical0Value0Content2.7
Performance profile

Strongest on business fit. The pulled-in value corner is the trade-off, and if the shape matters more than the price, this is your model.

Compare shapes side-by-side →

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.

© 2026 Design for Online Ltd. Registered in England and Wales No. 10328553. VAT Registered. Design for Online® and Forerunner® are registered trademarks.