Fable Shows Strong Planning Skills in Tetris
stuffyokodraws · x · 2026-07-18
The author tested Fable against Kimi K3 in Tetris, noting that Fable performed "surprisingly well" in long-horizon planning and optimization.
The video speed was set to 1.6x. While the post doesn't dive into extensive metrics, the key takeaway is how it demonstrates a model's planning capabilities in a mini-game requiring continuous decision-making.
Related event: Fable Shows Impressive Planning Skills in TetrisBench(2 posts)→
More from Models
- Same Echo Maze prompt, three frontier models: all passed visually but shipped the same hidden bug — eyishazyer · 2026-09-11
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11