แฅแตแซแแ แซแแฐแ แฅแจแฐแซ แซแ แฐแ แซแ แฎแแแต แแญ แแซแน
๐ค2
https://zcode.z.ai/cn
For Those of you looking for free codex like coding tool this is for you
NOTE: it only last till JUNE 19 - so you have 3 free days
download the app register in z.ai and start using
๐ Enjoy
For Those of you looking for free codex like coding tool this is for you
NOTE: it only last till JUNE 19 - so you have 3 free days
download the app register in z.ai and start using
๐ Enjoy
ZCode
ZCode - ็ฎๅใ่ฟ
ๆทใๆฐๅดๅ่ถณ | GLM-5.2 ๅฎๆน้้
ๅผๅๅทฅๅ
ท
ZCode ๅฐๅผบๅคง็ AI Agents ไธ็ฐๆๅทฅๅ
ท้พ็ปๅ๏ผๅธฎๅฉไฝ ๅจ็ๆๆต็จไธญๅฎๆ่งๅใ็ผ็ ใ่ฏๅฎกไธไธ็บฟใ
Yared's log ๐ซ pinned ยซhttps://zcode.z.ai/cn For Those of you looking for free codex like coding tool this is for you NOTE: it only last till JUNE 19 - so you have 3 free days download the app register in z.ai and start using ๐ Enjoyยป
Yared's log ๐ซ
https://zcode.z.ai/cn For Those of you looking for free codex like coding tool this is for you NOTE: it only last till JUNE 19 - so you have 3 free days download the app register in z.ai and start using ๐ Enjoy
i tested it and its impressive like 1.5 x codex impressive
Please open Telegram to view this post
VIEW IN TELEGRAM
Yared's log ๐ซ
https://zcode.z.ai/cn For Those of you looking for free codex like coding tool this is for you NOTE: it only last till JUNE 19 - so you have 3 free days download the app register in z.ai and start using ๐ Enjoy
Try this 2 days left - it will not ask for visa card or anything
Forwarded from Yared's Log Chat
โญ VibeThinker-3B is released โ a dense 3B model for frontier-level verifiable reasoning.
๐ Reasoning: 94.3 on AIMEโ26, 76.4 on IMO-AnsBench, and 80.2 Pass@1 on LCB v6; with CLR, AIMEโ26 improves to 97.1 and IMO-AnsBench to 80.6.
๐ป OOD Coding: On recent unseen LeetCode weekly contests, VibeThinker-3B passes 123/128 (96.1%) first-attempt Python submissions.
โก Efficiency: Only 3B parameters, yet reaching the performance range of much larger top-tier reasoning models.
๐จ This model was not trained on tool-calling or agent-based programming data. We therefore do not recommend using it for tasks that involve function calling, API orchestration, or autonomous coding agents. For programming tasks, we recommend using this model on competitive programming problems (e.g., LeetCode-style).
The Model hugging face repo have a size below 7GB that is impressive for the benchmark the shaw
https://huggingface.co/WeiboAI/VibeThinker-3B
๐ Reasoning: 94.3 on AIMEโ26, 76.4 on IMO-AnsBench, and 80.2 Pass@1 on LCB v6; with CLR, AIMEโ26 improves to 97.1 and IMO-AnsBench to 80.6.
๐ป OOD Coding: On recent unseen LeetCode weekly contests, VibeThinker-3B passes 123/128 (96.1%) first-attempt Python submissions.
โก Efficiency: Only 3B parameters, yet reaching the performance range of much larger top-tier reasoning models.
๐จ This model was not trained on tool-calling or agent-based programming data. We therefore do not recommend using it for tasks that involve function calling, API orchestration, or autonomous coding agents. For programming tasks, we recommend using this model on competitive programming problems (e.g., LeetCode-style).
The Model hugging face repo have a size below 7GB that is impressive for the benchmark the shaw
https://huggingface.co/WeiboAI/VibeThinker-3B
Please open Telegram to view this post
VIEW IN TELEGRAM
Please open Telegram to view this post
VIEW IN TELEGRAM