OpenRouter Launches Fusion Model That Matches Fable 5 at Half the Cost, Scores 69% vs 65.3%

DEEPSEEK-2.72%
According to monitoring by Beating, OpenRouter has released the Fusion composite model interface, which distributes user prompts in parallel to multiple large language models and synthesizes outputs through a judge and synthesis model. In Perplexity AI's DRACO deep research benchmark, a multi-model combination achieved 69.0%, surpassing Fable 5's standalone score of 65.3%. A low-cost panel combining Gemini 3 Flash, Kimi K2.6, and DeepSeek V4 Pro scored 64.7% at half the inference cost, closing the gap with Fable 5 to just 0.6 percentage points.
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.
Comment
0/400
No comments