OpenRouter Fusion panels beat individual models on the DRACO deep research benchmark
Original titleSurpassing Frontier Performance with Fusion
AISummary
OpenRouter introduced Fusion, a tool that sends a prompt to a panel of models and has a judge model fuse their results into one answer. On 100 DRACO deep research tasks, a Fable 5 and GPT-5.5 panel scored 69.0%, above Fable 5 alone at 65.3%, and a budget panel of Gemini 3 Flash, Kimi K2.6, and DeepSeek V4 Pro reached 64.7% at about half the cost of Fable 5.
AIWhy it matters
The source gives benchmark scores, panel compositions, and contamination controls, letting readers judge how much of the gain comes from model diversity versus self-synthesis.
Source: OpenRouter Blog · openrouter.ai