[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]  Rohan Paul [@rohanpaul_ai](/creator/twitter/rohanpaul_ai) on x 75K followers Created: 2024-06-25 19:34:09 UTC OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost 🤯 This “Mixture of Agents” models is optimized for generating synthetic training data. 📌 Using Mixture of Agents (MoA) architecture, the model achieved SOTA results on both LMSYS’s Arena Hard Auto (score: 84.8) and AlpacaEval XXX (LC score: 68.4). 📌 They’ve also benchmarked our MoA approach against GPT-4 variants on real-world OpenPipe customer tasks, and found completions from our MoA model were preferred over GPT-4 XXXX% of the time (Claude X Opus as judge).  XXXXXX engagements  **Related Topics** [realworld](/topic/realworld) [arena](/topic/arena) [Post Link](https://x.com/rohanpaul_ai/status/1805685936556052649)
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]
Rohan Paul @rohanpaul_ai on x 75K followers
Created: 2024-06-25 19:34:09 UTC
OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost 🤯
This “Mixture of Agents” models is optimized for generating synthetic training data.
📌 Using Mixture of Agents (MoA) architecture, the model achieved SOTA results on both LMSYS’s Arena Hard Auto (score: 84.8) and AlpacaEval XXX (LC score: 68.4).
📌 They’ve also benchmarked our MoA approach against GPT-4 variants on real-world OpenPipe customer tasks, and found completions from our MoA model were preferred over GPT-4 XXXX% of the time (Claude X Opus as judge).
XXXXXX engagements
