Brian Samek
About Me Benchmarks Blog BJJ Flowchart

This is a list of AI benchmarks I’m watching. Last updated November 2, 2026.

  • ALE-Bench
  • ARC Prize
  • Agent Arena and Arena Text
  • Artificial Analysis
  • DeepSWE
  • Epoch AI Models
  • FrontierCode
  • GameDevBench
  • Gert Labs Rankings
  • LiveBench
  • Mercor Apex
  • RuneScape Bench
  • SimpleBench
  • Toloka Arena
  • Vals Index
  • Vending-Bench 2 and Vending-Bench Arena
  • VoxelBench
  • WeirdML