Epoch AI's new SpireClimb benchmark has AI models play the notoriously hard card game Slay the Spire through a screen-and-mouse computer-use setup. At the game's maximum difficulty, where frontier models won no runs a few months ago, GPT-6.1 Sol now wins 20% of max-difficulty Slay the Spire runs; top humans win 80%+
Epoch AI's new SpireClimb benchmark measures AI models' ability to play the card game Slay the Spire through a screen-and-mouse interface. GPT-6.1 Sol achieved a 20% win rate at the game's maximum difficulty, "Ascension 20 Heart." This is an increase from a 0% win rate a few months prior, though it remains below the 80%+ win rates of top human players.
Verified 2026-10-22
Track with InsiderWhy it matters
Long games with hidden information test planning and computer use over hours, the same skills agents need to finish real work end to end, and that gap is closing fast.
More on Models
- AI models can now win gold at the International Mathematical Olympiad, yet Stanford's 2026 AI Index found they still fumble a task most children master early. Across ClockBench's 180 clock designs and 720 questions, the top model, GPT-5.4 High, read analog clocks correctly only 50.6% of the time, versus 90.1% for humans
- After briefly nearly closing in 2024, the performance gap between the best closed-weight and open-weight AI models widened again on the Arena leaderboard. As of March 2026, Stanford's 2026 AI Index finds the top closed model leads the top open model by 3.3%, up from a 0.5% lead in August 2024
- Stanford's 2026 AI Index tracks how AI models perform on GPQA Diamond, a set of PhD-level chemistry and physics questions designed to resist Google searches. Mean model accuracy on the benchmark reached 93% in 2025, compared with an expert human validator baseline of 81.2% -- AI models now beat PhD-level experts by 12 points on GPQA Diamond
FREE · NO CARD
Facts like this, six days a week
The Daily Receipts on weekdays, The Weekly Brief on Saturday — six sourced facts a day by email, two more than the free site shows. Every one traced to the filing it came from. Free.
Get the free daily briefFree · No card · Unsubscribe anytime
Join now and you start with 100 Receipts on The Receipts Ledger — your first step toward a free year of Insider or Pro. How it works →
See today's issue →