NeoHorse-1.5-Flash Preview Released
The story so far
Jiyuan Lüdòng has released the native Agent model NeoHorse-1.5-Flash Preview, which is based on Qwen3.8-Flash training, with a total of 180B parameters and 6B activation parameters, achieving score improvements in evaluations through recursive self-improvement (RSI) iterations. Jiyuan Lüdòng claims that after releasing NeoHorse-1 in September, the company will re-release the previous generation model back into the model pool to collect execution feedback for subsequent training and has expanded the model training scale to the Flash tier. The model is currently open for limited internal testing. This release continues the exploration of RSI in the NeoHorse series, expanding the model training scale from the initial 4B and 9B to the Flash tier.
AI-written from the reports · Updated 10 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- QbitAIJi Yuan Law Release NeoHorse-1.5-Flash Preview, Agent model RSI enters the second round of iteration
Ji Yuan Law Release Agent Native Model NeoHorse-1.5-Flash Preview, based on Qwen3.8-Flash training, 180B total parameters, 6B activation parameters, score improvement in Agents' Last Exam, Natural Language to Repository and other evaluations. This model iterates through recursive self-improvement (RSI) and combines the OpenSquilla platform to achieve differential diagnosis of multiple models and online learning, now open for limited internal testing.