Qwen2 Instruct 72B
Intelligence
11.7
#419/523
Coding
—
Math
—
Speed
—
Pricing
—
Qwen2 Instruct 72B is Alibaba’s latest model designed for various AI applications. With an Intelligence Index of 11.7, it aims to provide efficient processing capabilities for professional users.
When to Use Qwen2 Instruct 72B
✓ Best For
- Natural language understanding tasks.
- Content generation.
- AI-assisted coding.
✗ Not Ideal For
- High-speed processing needs, as it currently has a speed of 0 tok/sec.
- Complex mathematical computations, as specific indices are not available.
How Qwen2 Instruct 72B Compares
Intelligence Index · Higher is better
xAILG AI ResearchAlibabaMistralGoogle
Benchmark Profile
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (23)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 11.7 | |
| MMLU-Pro | 622% | |
| GPQA | 371% | |
| LiveCodeBench | 159% | |
| HLE | 37% | |
| SciCode | 22.9% | |
| AIME | 14.7% | |
| MATH 500 | 70.1% | |
| ARC-C | 68.9% | |
| BBH | 82.4% | |
| C-Eval | 83.8% | |
| CMMLU | 90.1% | |
| EvalPlus | 79% | |
| GSM8k | 91.1% | |
| HellaSwag | 87.6% | |
| HumanEval | 86% | |
| MATH | 59.7% | |
| MBPP | 80.2% | |
| MMLU | 82.3% | |
| MultiPL-E | 69.2% | |
| TheoremQA | 44.4% | |
| TruthfulQA | 54.8% | |
| Winogrande | 85.1% |
Data: Artificial Analysis · Updated: April 10, 2026
Frequently Asked Questions (15)
When was Qwen2 Instruct 72B released?
Qwen2 Instruct 72B was released on June 7, 2024.
Who created Qwen2 Instruct 72B?
Qwen2 Instruct 72B was created by Alibaba.
How intelligent is Qwen2 Instruct 72B?
Qwen2 Instruct 72B scores 12 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other open weight non-reasoning models of similar size (median: 13).
Is Qwen2 Instruct 72B a reasoning model?
No, Qwen2 Instruct 72B is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
What input modalities does Qwen2 Instruct 72B support?
Qwen2 Instruct 72B supports text only input.
What output modalities does Qwen2 Instruct 72B support?
Qwen2 Instruct 72B supports text only output.
Can Qwen2 Instruct 72B process images?
No, Qwen2 Instruct 72B does not support image input. It can only process text.
Is Qwen2 Instruct 72B multimodal?
No, Qwen2 Instruct 72B is not multimodal. It only supports text only input.
What is the context window of Qwen2 Instruct 72B?
Qwen2 Instruct 72B has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Is Qwen2 Instruct 72B open source?
Yes, Qwen2 Instruct 72B is open weights. The model weights are publicly available and can be downloaded for self-hosting.
How many parameters does Qwen2 Instruct 72B have?
Qwen2 Instruct 72B has 72 billion parameters.
What is the license for Qwen2 Instruct 72B?
Qwen2 Instruct 72B is released under the Tongyi Qianwen LICENSE AGREEMENT license. This license allows commercial use.
How does Qwen2 Instruct 72B perform on benchmarks?
Qwen2 Instruct 72B achieves a score of 12 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Is Qwen2 Instruct 72B available via API?
Qwen2 Instruct 72B is an open weights model that can be self-hosted.
Where can I use Qwen2 Instruct 72B?
Qwen2 Instruct 72B is an open weights model that can be downloaded and self-hosted.
