TokenRhythm Unveils New Agent Model: 180B Total Parameters, Limited Closed Beta Now Open

Deep News11-10

TokenRhythm has released its Agent-native model NeoHorse-1.5-Flash Preview.

The model is trained on Qwen3.8-Flash, with 180B total parameters and 6B activated parameters, focusing on improving Agent task execution and software engineering capabilities.

According to the company's published comparative evaluation, compared with the base model, the new model's overall score on Agents' Last Exam increased by 9.23 points, and its overall score on the Natural Language to Repository evaluation increased by 5.92 points.

Among these, physical science tasks improved by more than 20 points, and there were also improvements in development tools and testing, Web development, and security authentication and encryption.

This release continues the NeoHorse series' exploration of recursive self-improvement (RSI), which TokenRhythm calls the "second lap" of this mechanism.

After releasing NeoHorse-1 in September, the company put the previous-generation model back into the model pool, collected execution feedback in actual tasks, and then used this experience for subsequent training. The scale of model training also expanded from 4B and 9B in the first round to the Flash tier.

This path relies on the TokenRhythm multi-model platform and the open-source Agent product OpenSquilla.

The routing system provides signals of task capability requirements, while multi-model fusion allows multiple frontier models to handle the same task, forming comparable execution results.

The differences between NeoHorse and these results are used to identify capability shortcomings, determine training directions, and turn them into learning signals.

On the day after the model release, TokenRhythm also updated OpenSquilla, improving this execution foundation.

The new version selects model tiers according to task intent, continues to use the original tier when continuing a task, and upgrades tier by tier when redoing it; at the same time, it supports independent updates to the TokenRhythm and OpenRouter recommended solutions, so users can preview differences and confirm applications without upgrading the client.

The recommended configuration for this period was also adjusted according to the November model rankings, enabling model selection on the execution side to keep updating in line with evaluation results.

Disclaimer: Investing carries risk. This is not financial advice. The above content should not be regarded as an offer, recommendation, or solicitation on acquiring or disposing of any financial products, any associated discussions, comments, or posts by author or other users should not be considered as such either. It is solely for general information purpose only, which does not consider your own investment objectives, financial situations or needs. TTM assumes no responsibility or warranty for the accuracy and completeness of the information, investors should do their own research and may seek professional advice before investing.

Comments

We need your insight to fill this gap
Leave a comment