Loading...
Market
In which AI competition will Phi-4 top perform by end of 2025?
2
Resolution / Starting Odds
NeurIPS • 25%
ICML • 25%
AAAI • 25%
Other • 25%
Official competition results and rankings
Story
Microsoft's Phi-4 Model, With 14 Billion Parameters, Outperforms Larger AI Models in Math
Dec 13, 2024, 04:36 AM
Microsoft Corp. has unveiled Phi-4, a new small language model with 14 billion parameters, developed by Microsoft Research. This model specializes in complex reasoning and math, demonstrating exceptional performance in various benchmarks. Phi-4 outperforms larger models like GPT-4, Claude 3.5, Llama 3.3, and Gemini Pro 1.5 in competition math and on math benchmarks, achieving a 91.8% accuracy on AMC 10/12 math competition problems. The model's development focuses on synthetic data quality and innovative training techniques, rather than increasing model size, highlighting a shift from the traditional 'scale-first' mindset in AI. Phi-4 scored 56.1 on GPQA, 80.4 on MATH, and 82.6 on HumanEval benchmarks. It is currently available on Azure AI Foundry and will soon be accessible on Hugging Face.
View original story
Similar markets
Llama 3.1 405B • 25%
GPT-4o • 25%
Claude Sonnet 3.5 • 25%
Other • 25%
Google's Gemini • 25%
OpenAI's GPT • 25%
Microsoft's Azure AI • 25%
Other • 25%
Meta's Llama 3.1-70B • 25%
OpenAI's GPT-4 • 25%
Google's Bard • 25%
Other • 25%
Claude 3.5 Sonnet • 33%
GPT-4o • 33%
Google's AI Model • 33%
Outperforms all models • 25%
Outperforms AlphaFold3 but not ESM3 • 25%
Outperforms ESM3 but not AlphaFold3 • 25%
Does not outperform either • 25%
Winning a Kaggle competition • 25%
Winning a NeurIPS competition • 25%
Winning an ImageNet challenge • 25%
Other major competition • 25%
Efficiency improvements • 25%
Enhanced reasoning capabilities • 25%
Broader language support • 25%
Increased safety features • 25%
International Mathematical Olympiad • 25%
Kaggle Competition • 25%
DARPA Challenge • 25%
Other • 25%