[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.]

![rohanpaul_ai Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::2588345408.png) Rohan Paul [@rohanpaul_ai](/creator/twitter/rohanpaul_ai) on x 73.9K 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).

![](https://pbs.twimg.com/media/GQ8VDmLWUAAn49p.jpg)

XXXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1805685936556052649/c:line.svg)

**Related Topics**
[realworld](/topic/realworld)

[Post Link](https://x.com/rohanpaul_ai/status/1805685936556052649)