Loading...
Market
Which AI model will achieve the highest score in the next Arena Hard benchmark test by Q1 2025?
2
Resolution / Starting Odds
Nemotron 70B • 25%
ChatGPT4o • 25%
Sonnet 3.5 • 25%
Other • 25%
Official results of the Arena Hard benchmark test
Story
Nvidia'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
Similar markets
Meta's Llama 3.1-70B • 25%
OpenAI's GPT-4 • 25%
Google's Bard • 25%
Other • 25%
Llama 3.1 405B • 25%
GPT-4o • 25%
Claude Sonnet 3.5 • 25%
Other • 25%
ChatGPT-4o • 25%
Google's Gemini • 25%
Another AI model • 25%
No clear leader • 25%
DeepSeek-R1-Lite-Preview • 25%
OpenAI's o1-preview • 25%
Google DeepMind's model • 25%
Other • 25%
Google's Gemini • 25%
OpenAI's GPT • 25%
Microsoft's Azure AI • 25%
Other • 25%
Claude 3.5 Sonnet • 33%
GPT-4o • 33%
Google's AI Model • 33%
Llama 3-70B • 25%
GPT-4 • 25%
Claude 2.0 • 25%
Other • 25%
Claude 3.5 Sonnet • 33%
GPT-4o • 33%
Gemini • 34%
FLUX 1.1 Pro • 25%
FLUX 1.0 Pro • 25%
Competitor Model 1 • 25%
Competitor Model 2 • 25%
OpenAI o1-preview • 25%
Anthropic Claude 3.5 Sonnet • 25%
OpenAI o1 mini • 25%
Other • 25%
ChatGPT-4o • 25%
Gemini 1.5 Pro • 25%
Claude-3.5 • 25%
Other • 25%
OpenAI's O1 model • 25%
GPT-4 • 25%
Gemini • 25%
Anthropic's Claude • 25%