GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
1–10 of 35 posts
Re: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
#2GLM-5V-Turbo is a model I wanted to like due to its speed and API reliability, but it didn't perform well in our coding and reasoning testing. More recent open source models have made it obsolete. GLM 5.1 is so many light years ahead of it on everything except speed, that I'm not sure why it's still being served.
Comprehensive evaluation results at https://gertlabs.com/rankings
Re: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
#3z.ai will use quantized models in off hours. Buyer beware
Re: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
#4GLM-5V-Turbo is a model I wanted to like due to its speed and API reliability, but it didn't perform well in our coding and reasoning testing. More recent open source models have made it obsolete. GLM 5.1 is so many light years ahead of it on everything except speed, that I'm not sure why it's still being served. Comprehensive evaluation results at https://gertlabs.com/rankings
GLM-5.1 does not support image input.
Re: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
#5GLM-5V-Turbo is a model I wanted to like due to its speed and API reliability, but it didn't perform well in our coding and reasoning testing. More recent open source models have made it obsolete. GLM 5.1 is so many light years ahead of it on everything except speed, that I'm not sure why it's still being served. Comprehensive evaluation results at https://gertlabs.com/rankings
I think the point is to use them both with GLM 5.1 delegating vision tasks to GLM-5V-Turbo
Re: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
#6z.ai will use quantized models in off hours. Buyer beware
Do you have proof for this?
Re: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
#7z.ai will use quantized models in off hours. Buyer beware
I have a subscription and I have not seen any difference in performance during on/off hours. What exactly are you basing this on?
Re: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
#8GLM-5V-Turbo is a model I wanted to like due to its speed and API reliability, but it didn't perform well in our coding and reasoning testing. More recent open source models have made it obsolete. GLM 5.1 is so many light years ahead of it on everything except speed, that I'm not sure why it's still being served. Comprehensive evaluation results at https://gertlabs.com/rankings
This may be a strange request, but is it at all possible to include Cursor's Composer models in your tests?
Re: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
#9GLM-5V-Turbo is a model I wanted to like due to its speed and API reliability, but it didn't perform well in our coding and reasoning testing. More recent open source models have made it obsolete. GLM 5.1 is so many light years ahead of it on everything except speed, that I'm not sure why it's still being served. Comprehensive evaluation results at https://gertlabs.com/rankings
>but it didn't perform well in our coding and reasoning testing
>Comprehensive evaluation results at https://gertlabs.com/rankings
But if you go to the linked site, it seems like the only thing that's part of the evaluation is how well the models play various games? I suppose that counts as "reasoning", but I don't see how coding ability tested?
Re: GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents
#10Click coordinates. Agentic GUI is really annoying when the multi-modal agent cannot click on x,y coordinates.
I tested Qwen3.6, Gemma4, Nemotron3-nano-omni. They fully hallucinate x,y coords. (did not try GLM-5V yet)
GPT-5.5 can easily do it. But also Vocaela, a tiny 500M model, is quite good at it. Hope they improve the training for x,y clicking soon on the smallish multi-modals.
Recently slopped a http service together just so my local models can click, instead of relying on all the wild ways agents currently hack into the browser (browser-use, browser-harness, agent-browser, dev-browser etc) https://github.com/julius/vocaela-click-coords-http