Epoch AI Benchmark Shows Frontier Models Beating Slay the Spire 90% of Games
Epoch AI's SpireClimb benchmark shows frontier models now win over 90% of Slay the Spire games on the easiest difficulty, up from near-zero six months ago. GPT-6.1 Sol leads the board, though top human players still dominate the hardest difficulty.
2026-10-15 ~ 2026-10-15 · 2 related posts
- Frontier AI models now win 90%+ of Slay the Spire runs, up from barely winning six months ago — NathanpmYoung · 2026-10-15
- Epoch AI game benchmark: GPT-6.1 Sol leads Slay the Spire but still trails top humans — Jsevillamol · 2026-10-15