According to the LMSYS Leaderboards, Google’s new AI model Gemini 1.5 Pro has defeated the previous champion, GPT-4o, and Claude-3.5 to come on top.
Well, well, well, look who’s sitting pretty at the top of the AI leaderboard! Google’s Gemini 1.5 Pro has finally dethroned the reigning champs, GPT-4o and Claude-3.5, in a stunning upset.
You can test these models and their weights, and see the leaderboard rankings on the LMSYS website.
Gemini 1.5 Pro flexed its muscles in the Arena, racking up an impressive 1300 points and snagging the top spot on the Vision Leaderboard. It’s like the AI equivalent of winning an Olympic gold medal but with way less spandex and sweat.
So, what makes Gemini so special? It’s a multilingual whiz kid, acing tasks in multiple languages. And it’s got the competition beat when it comes to the brainy stuff like math, coding, and handling those tricky prompts.
Logan Kilpatrick (Google AI Studio lead) announced the new model weight in a tweet:
Soon afterward, based on the ranking on LMSYS Arena, the model was at the #1 spot. The LMSYS account also tweeted this:
This is a major milestone for Google, and it’s sure to shake things up in the AI world. The competition is heating up, and it’s anyone’s guess who’ll be on top next week. But for now, let’s give a big round of applause to Gemini 1.5 Pro for its impressive victory.
