Nous Research presents Hermes 4, our latest line of hybrid reasoning models. Hermes 4 builds on our legacy of user-aligned models with expanded test-time compute capabilities. Special attention was given to making the models creative and interesting to

Our latest language model, Hermes 4, is FREE through the entire holiday weekend!. Try an AI that's aligned to you.

RT @NousResearch: Nous Research presents Hermes 4, our latest line of hybrid reasoning models. Hermes 4 builds on….

RT @OpenRouterAI: Fourth model launch of the day 🔥 - introducing Hermes 4, from @NousResearch . Hermes 4 is trained for steerability and lo….

RT @jon_durbin: Excellent work from the @NousResearch team, as always! These were Proxima and Meridian on chutes ICYMI, poor Proxima didn't….

RT @pingToven: @NousResearch Congrats on the launch team! Live now on OpenRouter:

RT @nebiusaistudio: Nebius AI Studio 🤝@NousResearch . Introducing:.🔹 Hermes-4-70B .🔹 Hermes-4-405B . We’re proud to power Nous Chat with….

RT @lmstudio: NousResearch/Hermes-4-70B. • Hybrid reasoning model (toggle on/off).• Strong instruction following, creative writing.• Max co….

RT @joefioti: We're live hosting the latest and greatest reasoning model from Nous!.

Special thanks to our launch day partners - @chutes_ai, @nebiusai, and @luminal_ai - for serving these models and powering our new chat experience. Check out their platforms for additional options for API inference. And if you’re looking for support or a great AI community to.

In pursuit of producing models that are open, steerable and capable of producing the full range of human expression, we created a new benchmark, RefusalBench, that tests a model’s willingness to be helpful in a variety of scenarios commonly disallowed by both closed and open

Alongside these models, Nous Research releases a technical report that details the entirety of its creation process. The technical report includes a thorough set of evaluations of Hermes 4 and other popular LLMs, complete with the actual text-results of

You can try Hermes 4 in the new, revamped Nous Chat UI. Nous Chat has been reworked to include parallel interactions, completions mode, and a memory system, which is slowly being rolled out. We now provide a suite of open and closed models for this

RT @asankhaya: 1/10🧵 @nousresearch recently published an interesting study showing open models use 2-3x more tokens than closed models for….

Measuring Thinking Efficiency in Reasoning Models: The Missing Benchmark. We measured token usage across reasoning models: open models output 1.5-4x more tokens than closed models on identical tasks, but with huge variance depending on task type (up to

RT @Teknium1: The Arena-Hard eval environment is now merged to Atropos - enjoy scalable, flexible and modern evaluation with @lmsysorg's ar….

RT @Aboozle: Recently completed and merged my first RL environment into @NousResearch's Atropos! This environment is based on Word Hunt, wh….

Our Researcher in Residence @yaboilyrical will be discussing his work on SMC steering at UC Berkeley on Aug 3. Check out the blog on this work here: . Details below!.

The Psyche office hours is beginning in 20 minutes in our Discord - See you there!.