Math: RL environments and AI benchmarks

4 environments · 10 benchmarks · snapshot 2026-09-03

Scroll to zoom · drag to pan · ○ environment · ◇ benchmark · ● domain

RL environments 4

  1. Prime Intellect rl-list
  2. Sepal AI rl-list
  3. Ulam pavlovslist
  4. Hillclimb pavlovslist

AI benchmarks 10

  1. AIME 2025 Artificial Analysis · benchmarklist
  2. FrontierMath 2025-02-28 Private Neosignal Epoch AI · benchmarklist
  3. FrontierMath Tier 4 2025-07-01 Private Neosignal Epoch AI · benchmarklist
  4. GSM8K Huggingface Leaderboard API · benchmarklist
  5. OTIS Mock AIME 2024-2025 Neosignal Epoch AI · benchmarklist
  6. AIME Vals AI · benchmarklist
  7. HELM GSM8K Helm Classic GCS Json · benchmarklist
  8. AA AIME 2025 benchlm-benchmarks
  9. AIME 2023 benchlm-benchmarks
  10. AIME 2024 benchlm-benchmarks

Next: pick another domain. Tags come from the RL Engineering daily scrape, canonicalized nightly.