FLock Unveils THIS/THAT Model with 87.8% Success Rate

Decentralized AI platform FLock.io has announced that its open-source decision-making model 'THIS / THAT' has received official recognition and promotional support from the Alibaba Qwen team. THIS / THAT is based on Qwen 3.5 2B and was trained using synthetic data generated by Qwen Max. The model training was conducted on Alibaba Cloud infrastructure. According to benchmark results, version 1.2 of the THIS / THAT model achieved a success rate of 87.8% across 1,710 complex decision-making tasks. This figure is more than double the 40.6% success rate of version 1.0. In the same benchmark, OpenAI's GPT-5.6 recorded 81.6%, while Anthropic's Claude Opus 5 scored 83.4%. The number of parameters in THIS / THAT is 1.88 billion, and it is designed to make decisions without output tokens. The latency per decision is approximately 31.4 milliseconds (ms). FLock plans to explore practical applications of AI models through long-term collaboration with Qwen and Alibaba Cloud.

This content is provided for general informational purposes only and doesn't constitute financial, investment, legal, or tax advice. Any events, rewards, online promotions, or related information mentioned herein should not be considered a recommendation, solicitation, or invitation to purchase, sell, trade, or otherwise deal in any crypto assets. Crypto assets are highly volatile and may result in loss. The availability of WEEX services, products, and related events may vary by region. You are responsible for ensuring that your participation is in accordance with applicable local laws and regulations.