Loading...
Loading...
Browse all stories on DeepNewz
VisitNvidia's Nemotron 70B Surpasses ChatGPT4o and Sonnet 3.5 in Benchmarks, Now Available on Hugging Face MLX
Oct 16, 2024, 02:45 PM
Nvidia has introduced Nemotron 70B, an open-source AI language model that reportedly surpasses OpenAI's ChatGPT4o and Anthropic's Sonnet 3.5 in various performance benchmarks. Early assessments indicate that Nemotron 70B achieved higher scores on the Arena Hard benchmark (85.0) compared to ChatGPT3.5 (79.2) and GPT-4o (79.3), as well as outperforming them on AlpacaEval 2 and MT-Bench evaluations. The model is now accessible through the Hugging Face MLX community, allowing users to experience its capabilities firsthand. This development underscores Nvidia's growing influence in the AI sector and could reshape the competitive landscape dominated by established technology giants.
View original story
Markets
No • 50%
Yes • 50%
Popularity rankings or user engagement metrics on Hugging Face MLX
Yes • 50%
No • 50%
User adoption statistics on Hugging Face MLX platform
No • 50%
Yes • 50%
Official announcements from Nvidia or relevant press releases
Nemotron 70B • 25%
Other • 25%
Sonnet 3.5 • 25%
ChatGPT4o • 25%
Official results of the Arena Hard benchmark test
Other • 25%
Nemotron 70B • 25%
ChatGPT4o • 25%
Sonnet 3.5 • 25%
Download statistics from Hugging Face MLX platform
Anthropic • 25%
Other • 25%
Nvidia • 25%
OpenAI • 25%
Performance results from major AI benchmarks like Arena Hard, AlpacaEval 2, and MT-Bench