![](https://cdn.prod.website-files.com/65c7038117fcb5339e0c1065/660d5abb50c5d6c77fa6a565_Frame%201216260396.webp)
![](https://cdn.prod.website-files.com/65c7038117fcb5339e0c1065/660d5908cc9b8dcae549319e_ARC%20Benchmark%20Results.webp)
It’s time to come clean on these benchmark results.
We didn’t beat one of the models in our poll…we actually beat all four. 💪
This has firmly cemented our position as one of the most pre-eminent AI companies in the world. 🌐
See the results for yourself 📊
71.8 | Reactor Mk I ✅
— — — — — — —
65.58 | Google — Gemini Pro ❌
71.02 | OpenAI — GPT 3.5 Turbo ❌
55> | Meta — Llama 2 ❌
41.76 | Mistral — Mixtral ❌
Check out our score relative to the other AI models via an independent study conducted by Carnegie Mellon below👇 https://synthedia.substack.com/p/cmu-study-shows-gemini-pro-trails
Share this article