Models

QwenVL vs. CogVLM

Both

QwenVL

and

CogVLM

are commonly used in computer vision projects. Below, we compare and contrast

QwenVL

and

CogVLM

.

  QwenVL CogVLM
Date of Release
Model Type Multimodal Model Multimodal Model
Architecture
GitHub Stars 1900 25000

We ran seven tests across five state-of-the-art Large Multimodal Models (LMMs) on November 23rd, 2023. QwenVL passed at five of seven tests and CogVLM passed at five of seven tests.

Both models have their strengths and weaknesses. We encourage you to experiment with them on your own data to learn more about how they work.

For example, CogVLM passed at a document VQA task that involved asking for the price of a menu item, which Qwen-VL was unable to answer. With that said, CogVLM hallucinated an answer to a question about a movie scene, which Qwen-VL was able to answer.

Here are the results:

Based on our tests, QwenVL and CogVLM both perform well on a range of multimodal tasks.

Read more of our analysis.

Download the raw image results from our analysis.

QwenVL

Qwen-VL is an LMM developed by Alibaba Cloud. Qwen-VL accepts images, text, and bounding boxes as inputs. The model can output text and bounding boxes. Qwen-VL naturally supports English, Chinese, and multilingual conversation.

How to AugmentHow to LabelHow to Plot PredictionsHow to Filter PredictionsHow to Create a Confusion Matrix

CogVLM

that shows strong performanve in Visual Question Answering (VQA) and other vision tasks. CogVLM achieves state-of-the-art performance on a range of vision benchmarks.

How to AugmentHow to LabelHow to Plot PredictionsHow to Filter PredictionsHow to Create a Confusion Matrix

Compare QwenVL to other models

Compare CogVLM to other models

Deploy a computer vision model today

Join 250,000 developers curating high quality datasets and deploying better models with Roboflow.

Get started