{"id":41372,"date":"2025-10-08T07:11:46","date_gmt":"2025-10-08T14:11:46","guid":{"rendered":"https:\/\/www.yardi.com\/blog\/?p=41372"},"modified":"2026-02-27T02:23:51","modified_gmt":"2026-02-27T10:23:51","slug":"gpt%e2%80%91oss","status":"publish","type":"post","link":"https:\/\/www.yardi.com\/blog\/gpt%e2%80%91oss\/","title":{"rendered":"GPT\u2011OSS is here. Open weights? Yes. SOTA? Not quite."},"content":{"rendered":"
<\/figure>\n

Key takeaways<\/h2>\n

OpenAI\u2019s first open\u2011weight model since GPT\u20112, GPT\u2011OSS is strong, practical and genuinely useful, but it doesn\u2019t consistently top today\u2019s leaderboards. In this post I\u2019ll show where GPT\u2011OSS shines and where it lags behind leading open models like Qwen 3, DeepSeek R1\/V3, Kimi K2 and others. We\u2019ll also look at how to pick the right model for your use case, why open models matter and how the U.S. can keep pace.<\/p>\n

OpenAI is finally \u201copen\u201d, again! They released an open weight version of their GPT-2 model back in the day (2019), but since then it\u2019s been nothing but proprietary models all the way. Until now\u2026<\/p>\n

GPT-OSS<\/a> is an open weight model that is on par with GPT-4 as well as many of the other open weight models like Qwen 3<\/a>, DeepSeek R1\/V3<\/a> and Kimi K2<\/a>. It\u2019s not quite at the top of all the leaderboards (as GPT-5 is), but compared to other open US models like Llama and Gemma, it has certainly come to play.<\/p>\n

We\u2019re going to look at where GPT-OSS shines, where it lags, why open models are important and how the U.S. can continue to keep pace with China.<\/p>\n

GPT-OSS is pretty smart<\/h2>\n

With the release of GPT-OSS, OpenAI has closed the gap with leading open weight models such as Qwen 3, DeepSeek R1\/V3, Kimi K2 and Llama across almost every benchmark and has regained the throne as the top dog in the U.S.-based open weight LLM space. <\/p>\n

Here are charts from some of my favorite leaderboards, which test everything from reasoning to coding ability, so you can see how GPT-OSS stacks up against the competition.<\/p>\n

Artificial Analysis<\/a><\/p>\n

\"\"<\/figure>\n

LMArena<\/a><\/p>\n

\"\"<\/figure>\n

LiveBench<\/a><\/p>\n

\"\"<\/figure>\n

Vellum<\/a><\/p>\n

\"\"<\/figure>\n

While there were several issues with the release of GPT-5, namely the challenges with its internal router that decides how much thinking to do, as well as the positioning of it as a true AGI, GPT-OSS has not suffered from the same problems. Partly, this is because GPT-OSS doesn\u2019t include a router. There are simply two versions, gpt-oss-120b and gpt-oss-20b. Both are reasoning models with excellent instruction following and tool use, making them extremely useful for many agentic tasks.<\/p>\n

Why open models matter<\/h2>\n

Open models, including models that are open weight<\/strong> (where the model weights, also known as the trained parameters, are made available to download and use) and open source<\/strong> (where not just the model weights but also the training data, methodology, code and architecture are shared) allow the community to benefit from the research that goes into building the models. These models can also be downloaded and used, essentially for free, as opposed to the pay-per-token licensing model of proprietary models like ChatGPT, Claude or Gemini. Finally, open models can be modified, either via a process called fine tuning, where additional training is done to help them perform better in certain domains, or via distillation, where the essence of the model\u2019s knowledge and intelligence is retained, yet they can run on less powerful hardware at the cost of slight degradation in performance.<\/p>\n

In addition to the above, the development of open models ensures that Artificial Intelligence does not remain the domain of a few large corporations that control the entire ecosystem. This is very much in parallel to the open source software movement that has allowed Linux to power much of the world\u2019s economy rather than relying on companies like Microsoft or Oracle.<\/p>\n

Where GPT\u2011OSS stacks up vs. Qwen 3, DeepSeek R1\/V3 & Kimi K2<\/h2>\n

Let\u2019s take a look at how these leading open weight models compare and why you might want to pick one over another for a particular task.<\/p>\n

GPT-OSS<\/strong><\/a> (<\/strong>OpenAI<\/strong><\/a>)<\/strong> \u2014 Text\u2011only, efficient, easy to run<\/em><\/p>\n