#mathematics
- Google DeepMind's AI Co-Mathematician Reaches 48% on FrontierMath Tier 4 Google DeepMind research
- SU-01: Gold-Medal-Level Olympiad Reasoning via Curriculum SFT and Two-Stage RL SU-01 Team research
- SOOHAK: Frontier LLMs Solve Hard Math But Fail to Recognize Unsolvable Problems research
- OpenAI's Next Model Astra Solves Ten Open Problems in Math and Theoretical CS OpenAI research
- Claude Research Model Raises Riemann Zeta Zero Lower Bound from 41.6% to 67.2% Anthropic research
- MaxProof: MiniMax Model Exceeds IMO and USAMO Gold-Medal Thresholds on Formal Math MiniMax research
- Mistral Releases Leanstral 1.5: Open Formal-Verification Model for Lean 4 Mistral research
- AI Co-Mathematician: Google DeepMind Achieves 48% on FrontierMath Tier 4 Google DeepMind research
- LLM-Driven Formal Mathematics Review: Where Current Systems Fall Short UCLA research
- Soohak: 64 Mathematicians Build Research-Level Benchmark That Stumps Frontier LLMs Seoul National University research
- AdvancedMathBench: Benchmark Suite for Advanced Mathematical Proof Generation and Verification InternLM research