Google's updated Gemini 1.5 Pro and Flash models have achieved significant rankings in the AI leaderboard. The Gemini 1.5 Pro model now ranks second overall, closing in on GPT-4, and tops the Chinese and French leaderboards. The Gemini 1.5 Flash model ranks ninth, outperforming notable models such as Llama-3-70B. These models offer lower cost and latency, making them advantageous for developers. The Flash model ties with Opus in coding, longer query, and Chinese categories. The Pro model has shown significant improvement since its April version, while the Flash model is noted for its speed and capability.
The performance of Gemini 1.5 Flash is the real takeaway. It's priced roughly similar to Claude Haiku, but in this leaderboard it's performing better than Claude Sonnet. https://t.co/zNiXe4O69d
We released an updated Gemini 1.5 Pro at IO, and a super fast yet capable Flash model. They're both very strong models, on LMSys the 1.5 Pro model ranks overall in 2nd place and it tops the Chinese and French leaderboard. On a personal note, the 1.5 series are the first LLMs… https://t.co/wnuTJ1yFz3
Gemini 1.5 Flash is so strong. https://t.co/B0A2Er6sEZ
Wow! Gemini 1.5 Pro comes to second place in the chat arena lol And Flash at 9 beating LLAMA-3-70B and haiku (and being super cheap). Google crushed that one. https://t.co/PjqSdDjhwt
Highlighting categories where Gemini 1.5 Flash is matching the heavy weights Why it matters? Cost and latency is lower for developers to take advantage of. Coding, Longer Query and Chinese Ties with Opus and GPT-4 respectively. https://t.co/dVz2SJaJri https://t.co/wcVek08yaJ
Great to see our updated Gemini 1.5 Pro/Advanced on the leaderboard. Gemini 1.5 Flash is doing amazing well too. It's been an amazing journey improving these models over time with an awesome team. And we're just getting started. 🚀🚀 https://t.co/eQEubx8spb
Big news – Gemini 1.5 Flash, Pro and Advanced results are out!🔥 - Gemini 1.5 Pro/Advanced at #2, closing in on GPT-4o - Gemini 1.5 Flash at #9, outperforming Llama-3-70b and nearly reaching GPT-4-0125 (!) Pro is significantly stronger than its April version. Flash’s cost,… https://t.co/zekXBVYQlC
We added cost calculations for Gemini 1.5 Pro and Gemini 1.5 Flash! https://t.co/JtMo0v9y9U