Epoch AI Introduces SpireClimb Benchmark and Plans Gameplay Video Archive

2 reports 1 reporting sources 8 hours agoNew

Understand the event

AI overview

Epoch AI introduced SpireClimb to evaluate frontier AI models on Slay the Spire, reporting win rates above 90% at the easiest difficulty and up to 20% at the hardest. Epoch AI said frontier models could barely beat the game six months earlier. Epoch AI also said it had recorded more than a thousand runs of Slay the Spire and its sequel for SpireClimb and would publish them on YouTube over the coming weeks, with subtitles showing the models’ in-game thinking. The videos are reconstructed from model play data rather than recorded live. Epoch AI said it does not plan to add future models’ runs to the archive.

Generated by AI from reports · Updated 7 hours ago

Latest development10/17 05:03 (UTC+8)

Epoch AI to publish over a thousand SpireClimb gameplay recordings Epoch AI · X

Developments

2 developments

10/17 05:03 (UTC+8) · 1 reports
Epoch AI Shares Reconstructed SpireClimb Gameplay Videos
Epoch AI · X：Epoch AI to publish over a thousand SpireClimb gameplay recordings
10/15 03:59 (UTC+8) · 1 reports
Epoch AI Introduces the SpireClimb Benchmark
Epoch AI · X：Epoch AI’s SpireClimb benchmark shows frontier models winning up to 20% of hardest runs

Report timeline

Follow the reports to explore different sides of the event.

10/17

05:03
Epoch AI · X
Epoch AI to publish over a thousand SpireClimb gameplay recordings
Epoch AI recorded over a thousand runs of Slay the Spire and its sequel for SpireClimb and will publish them over the coming weeks with subtitles showing models’ in-game thinking. The videos are reconstructed from model play data rather than recorded live; the archive will not include future models’ runs. Featured run: https://www.youtube.com/watch?v=IfxMBWGRzGU Playlist: https://www.youtube.com/playlist?list=PLPKlbQAkw6Tw

10/15

03:59
Epoch AI · X
Epoch AI’s SpireClimb benchmark shows frontier models winning up to 20% of hardest runs
Six months ago, frontier AI models could barely beat Slay the Spire. Now, according to our new SpireClimb benchmark, they win 90%+ of runs at the easiest difficulty, and up to 20% of runs at the hardest. https://t.co/KvV5gD2RBh

Event heat trend

可比范围当前: 8
Peak within comparable coverage: 1010/17 06:00 (UTC+8)
近 24 小时变化: +105%

Trends compare the same continuously observed participants, which may cover fewer sources than current heat. Point or click to inspect hourly heat, or use left and right arrow keys.

Keep reading

Latest daily · Issue 24NVIDIA and AI4Bharat Introduce Nemotron-pretraining-Indic-v1 and an Open Data Generation Pipeline