Sponsored by
AdsCreator.com
zai-org / GLM-4.1V-9B-Base
Model's Last Updated: October 25 2025
image-text-to-text
Introduction of GLM-4.1V-9B-Base
Model Details of GLM-4.1V-9B-Base
GLM-4.1V-9B-Base
📖 View the GLM-4.1V-9B-Thinking
paper
.
💡 Try the
Hugging Face
or
ModelScope
online demo for GLM-4.1V-9B-Thinking.
📍 Using GLM-4.1V-9B-Thinking API at
Zhipu Foundation Model Open Platform
Model Introduction
Vision-Language Models (VLMs) have become foundational components of intelligent systems. As real-world AI tasks grow increasingly complex, VLMs must evolve beyond basic multimodal perception to enhance their reasoning capabilities in complex tasks. This involves improving accuracy, comprehensiveness, and intelligence, enabling applications such as complex problem solving, long-context understanding, and multimodal agents.
Based on the GLM-4-9B-0414 foundation model, we present the new open-source VLM model GLM-4.1V-9B-Thinking , designed to explore the upper limits of reasoning in vision-language models. By introducing a "thinking paradigm" and leveraging reinforcement learning, the model significantly enhances its capabilities. It achieves state-of-the-art performance among 10B-parameter VLMs, matching or even surpassing the 72B-parameter Qwen-2.5-VL-72B on 18 benchmark tasks. We are also open-sourcing the base model GLM-4.1V-9B-Base to support further research into the boundaries of VLM capabilities.
Compared to the previous generation models CogVLM2 and the GLM-4V series, GLM-4.1V-Thinking offers the following improvements:
- The first reasoning-focused model in the series, achieving world-leading performance not only in mathematics but also across various sub-domains.
- Supports 64k context length.
- Handles arbitrary aspect ratios and up to 4K image resolution.
- Provides an open-source version supporting both Chinese and English bilingual usage.
Benchmark Performance
By incorporating the Chain-of-Thought reasoning paradigm, GLM-4.1V-9B-Thinking significantly improves answer accuracy, richness, and interpretability. It comprehensively surpasses traditional non-reasoning visual models. Out of 28 benchmark tasks, it achieved the best performance among 10B-level models on 23 tasks, and even outperformed the 72B-parameter Qwen-2.5-VL-72B on 18 tasks.
For video reasoning, web demo deployment, and more code, please check our GitHub .
Runs of zai-org GLM-4.1V-9B-Base on huggingface.co
706
Total runs
0
24-hour runs
-53
3-day runs
-57
7-day runs
-100
30-day runs
More Information About GLM-4.1V-9B-Base huggingface.co Model
Url of GLM-4.1V-9B-Base
GLM-4.1V-9B-Base huggingface.co Url
Provider of GLM-4.1V-9B-Base huggingface.co
Other API from zai-org
Total runs:
1.4M
Run Growth:
-470.7K
Growth Rate:
-33.68%
Total runs:
638.3K
Run Growth:
495.7K
Growth Rate:
83.64%
Total runs:
580.6K
Run Growth:
-309.0K
Growth Rate:
-48.82%
Total runs:
455.2K
Run Growth:
-861.7K
Growth Rate:
-189.30%
Total runs:
148.1K
Run Growth:
-19.8K
Growth Rate:
-12.88%
Total runs:
106.3K
Run Growth:
28.2K
Growth Rate:
26.72%
Total runs:
104.8K
Run Growth:
74.6K
Growth Rate:
81.53%
Total runs:
59.1K
Run Growth:
5.0K
Growth Rate:
8.24%
Total runs:
56.8K
Run Growth:
-6.7K
Growth Rate:
-11.79%
Total runs:
52.9K
Run Growth:
-33.0K
Growth Rate:
-60.86%
Total runs:
39.3K
Run Growth:
25.5K
Growth Rate:
65.50%
Total runs:
35.6K
Run Growth:
34.1K
Growth Rate:
95.90%
Total runs:
28.9K
Run Growth:
-56.8K
Growth Rate:
-167.27%
Total runs:
26.4K
Run Growth:
-223.8K
Growth Rate:
-847.74%
Total runs:
17.1K
Run Growth:
-29.1K
Growth Rate:
-157.97%
Total runs:
16.2K
Run Growth:
-5.9K
Growth Rate:
-36.19%
Total runs:
14.9K
Run Growth:
-498
Growth Rate:
-3.35%
Total runs:
14.2K
Run Growth:
-8.3K
Growth Rate:
-61.28%
Total runs:
11.9K
Run Growth:
-8.3K
Growth Rate:
-70.85%
Total runs:
11.2K
Run Growth:
-3.3K
Growth Rate:
-29.93%
Total runs:
11.0K
Run Growth:
-4.3K
Growth Rate:
-38.70%
Total runs:
7.7K
Run Growth:
-2.6K
Growth Rate:
-33.41%
Total runs:
6.5K
Run Growth:
1.2K
Growth Rate:
18.59%
Total runs:
6.1K
Run Growth:
-11.8K
Growth Rate:
-188.54%
Total runs:
5.9K
Run Growth:
-44.8K
Growth Rate:
-786.61%
Total runs:
2.1K
Run Growth:
418
Growth Rate:
19.92%
Total runs:
2.0K
Run Growth:
-3.3K
Growth Rate:
-165.63%
Total runs:
2.0K
Run Growth:
-5.4K
Growth Rate:
-190.24%
Total runs:
1.8K
Run Growth:
-11.3K
Growth Rate:
-621.78%
Total runs:
1.7K
Run Growth:
-548
Growth Rate:
-31.73%
Total runs:
1.4K
Run Growth:
-295
Growth Rate:
-21.95%
Total runs:
1.3K
Run Growth:
-692
Growth Rate:
-51.99%
Total runs:
1.0K
Run Growth:
621
Growth Rate:
59.71%
Total runs:
1.0K
Run Growth:
66
Growth Rate:
6.05%
Total runs:
959
Run Growth:
-2.0K
Growth Rate:
-211.37%
Total runs:
889
Run Growth:
420
Growth Rate:
47.24%
Total runs:
794
Run Growth:
112
Growth Rate:
14.93%
Total runs:
712
Run Growth:
-193
Growth Rate:
-27.18%
Total runs:
709
Run Growth:
221
Growth Rate:
31.17%
Total runs:
708
Run Growth:
-489
Growth Rate:
-69.46%
Total runs:
684
Run Growth:
43
Growth Rate:
6.42%
Total runs:
571
Run Growth:
76
Growth Rate:
13.19%
Total runs:
557
Run Growth:
-837
Growth Rate:
-150.27%
Total runs:
548
Run Growth:
-112
Growth Rate:
-21.54%
Total runs:
508
Run Growth:
-36
Growth Rate:
-7.13%
Total runs:
497
Run Growth:
233
Growth Rate:
46.88%
Total runs:
443
Run Growth:
-353
Growth Rate:
-79.68%
Total runs:
388
Run Growth:
-241
Growth Rate:
-58.07%
Total runs:
334
Run Growth:
89
Growth Rate:
26.65%
Total runs:
330
Run Growth:
-211
Growth Rate:
-57.03%
Total runs:
316
Run Growth:
18
Growth Rate:
5.70%
Total runs:
289
Run Growth:
-51
Growth Rate:
-17.65%
Total runs:
289
Run Growth:
-23
Growth Rate:
-7.96%
Total runs:
277
Run Growth:
-6
Growth Rate:
-2.17%
Total runs:
277
Run Growth:
-16
Growth Rate:
-5.71%
Total runs:
275
Run Growth:
-3
Growth Rate:
-1.09%
Total runs:
251
Run Growth:
0
Growth Rate:
0.00%
Total runs:
245
Run Growth:
36
Growth Rate:
14.69%
Total runs:
244
Run Growth:
-27
Growth Rate:
-11.07%
Total runs:
235
Run Growth:
24
Growth Rate:
10.21%
Total runs:
228
Run Growth:
3
Growth Rate:
1.32%