ZAYA1-8B Matches DeepSeek-R1 on Math With Just 760M Active Params
A new 8B MoE model called ZAYA1-8B achieves DeepSeek-R1-level math performance while activating only 760M of its 8B para…
🏷️ math reasoning
3 articles about 'math reasoning'
xAI Grok 3 Challenges GPT-4o in Math Benchmarks
Elon Musk's xAI releases Grok 3 with math reasoning scores rivaling OpenAI's GPT-4o, intensifying the LLM competition.
LG EXAONE 4.0 Adds Code and Math Reasoning
LG AI Research launches EXAONE 4.0 with enhanced code generation and mathematical reasoning, challenging global LLM lead…
1