Gemini 2.5 Pro: The New King of the AI Leaderboard!

Author(s): Kalash Vasaniya

Originally published on Towards AI.

Gemini 2.5 Pro is now the top AI on the AIder Polyglot Leaderboard.

Source: From https://aistudio.google.com

If you’re not a member but want to read this article, see this friend link here.

Step aside, there’s a new boss in town!

It can speak and understand lots of languages and assist people in solving issues quickly.

It’s like a super intelligent robot that is able to do lots of awesome things!

beating out a lot of other AI models on both accuracy and format abilities. It got 72.9% correct answers overall and 89.8% correct format.

Source: From https://aider.chat/docs/leaderboards/#aider-polyglot-benchmark-results

Gemini 2.5 Pro is unique among other AIs. It is quick and can respond to questions in numerous languages. Imagine having a friend who is able to communicate in English, Spanish, French, and even computer language

What questions would you put to your super-intelligent robot buddy if you could?

Gemini 2.5 Pro: 72.9% accurate, 89.8% accurate form, price unknown (mysterious, isn’t it?)Claude-3.7: 64.9% accurate, 91.7% accurate format, cost $8DeepSeek R1: 64.0% accurate, cost $13.29OpenAI (12–17): 61.7% correct, 90.5% well-formatted, cost $1.86OpenAI (2025–02–19): 60.4% accurate, cost $1.72o3-mini: 60.9% correct, 91.3% correct format, cost $18.16

You can see that Gemini 2.5 Pro is the most accurate overall. That’s like spelling a spelling bee with words from… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI