Gemini Ultra 2 Matches Humans on Grad Math Exams
Google DeepMind's Gemini Ultra 2 achieves human-level scores on graduate-level mathematics exams, marking a major milest…
🏷️ mathematical reasoning
6 articles about 'mathematical reasoning'
Grok 3.5 Beats GPT-5 on Math Reasoning Tests
Elon Musk's xAI releases Grok 3.5, which outperforms OpenAI's GPT-5 across major mathematical reasoning benchmarks.
Claude 4 Shatters Math Reasoning Benchmarks
Anthropic's Claude 4 sets new records on major mathematical reasoning benchmarks, outperforming GPT-4o and Gemini Ultra.
AlphaProof Wins Silver at Math Olympiad
Google DeepMind's AlphaProof system scores 28 out of 42 points at the 2024 International Mathematical Olympiad, narrowly…
MathNet Brings 30K Competition Problems to AI Benchmarking
MathNet introduces 30,000 competition-level math problems to rigorously test AI mathematical reasoning, raising the bar …
New Testing Framework 'Math Takes Two' Challenges the Authenticity of AI Mathematical Reasoning
A latest arXiv paper proposes the 'Math Takes Two' testing framework, which examines whether language models possess gen…
1