Concept · 7 episode(s)

Math Benchmarks

← all concepts

Definition

Math benchmarks measure model performance on mathematical reasoning, from grade-school word problems (GSM8K) to Olympiad and research-level questions (MATH, FrontierMath). They’ve been one of the most active arenas of capability progress and a recurring case study in benchmark saturation.

Episodes covering this

  1. 193
    Freeze Most of the Network: Where RL Improvement Actually Lives in a Transformer
    Is One Layer Enough? Training A Single Transformer Layer Can Match Full-Parameter RL Training
    Zhang, Hu, Glentis et al. · University of Minnesota·22 min·Jul 02, 2026
  2. 141
    How Two Tokens Reopened a Reasoning Method the Field Had Given Up On
    Demystifying Hidden-State Recurrence: Switchable Latent Reasoning with On-Policy Reinforcement Learning
    Yang, Chen, Wu et al. · HKUST(GZ)·29 min·Jun 12, 2026
  3. 133
    How MiniMax Turned a Reward-Hacking Disaster Into Olympiad Gold
    MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
    Chen, Zhang, Zhang et al. · MiniMax / The Chinese University of Hong Kong·34 min·Jun 12, 2026
  4. 048
    How a 30B Open Model Reached Olympiad Gold With the Right Recipe
    Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling
    Li, Zhan, Zhang et al. · Shanghai AI Laboratory / The Chinese University of Hong Kong·31 min·May 16, 2026
  5. 036
    Sparse Attention Was the Wrong Frame. Treat It as Geometry Instead.
    Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
    Dehghankar, Asudeh · University of Illinois Chicago·24 min·May 11, 2026
  6. 032
    A Sticky-Note for Every Layer: Letting Transformers Remember What They Were Just Thinking
    State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning
    Aviss · Fifth Dimension·23 min·May 09, 2026
  7. 009
    How Two Silent Library Bugs Quietly Invalidated a Wave of Reasoning Papers
    SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
    Limozin, Durech, Hoefler et al. · ETH AI Center·23 min·May 02, 2026

Worth reading next

Papers we haven't done a deep dive on yet, but would recommend on this topic.