Loading...
Market
Tencent AI Lab's method achieves a performance metric of 70+ on MATH by end of 2024?
4
Resolution / Starting Odds
Yes • 50%
No • 50%
Research publications or official reports from Tencent AI Lab
Story
Tencent AI Lab Unveils Persona-Driven Data Synthesis Method with 1 Billion Personas, Achieves Gains on MATH
Jul 1, 2024, 06:23 AM
Researchers at Tencent AI Lab Seattle have introduced a groundbreaking persona-driven data synthesis methodology that leverages a large language model (LLM) to create diverse synthetic data. This method utilizes a vast collection of 1 billion diverse personas curated from web data. The approach has demonstrated significant improvements in performance metrics, notably achieving massive gains on MATH, increasing from 49.6 to 64.9.
View original story
Similar markets
DeepSeek-R1-Lite-Preview • 25%
OpenAI's o1-preview • 25%
Google DeepMind's model • 25%
Other • 25%
Phi-4 • 25%
Gemini Pro • 25%
Llama 3.3 • 25%
Other • 25%
OpenAI's model • 25%
Deepseek-Math (7B) • 25%
Gemini 1.5 Pro (May) • 25%
GPT-4o • 25%
MMLU • 25%
ARC • 25%
GSM8K • 25%
None by June 30, 2024 • 25%
OpenAI's model • 25%
Deepseek-Math (7B) • 25%
Gemini 1.5 Pro (May) • 25%
GPT-4o • 25%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
Less than 90% • 25%
90%-94.99% • 25%
95%-99.99% • 25%
100% • 25%
