banteg Launches Sokoban Eval for LLM Planning
Developer banteg launched a live Sokoban eval probing LLM planning and state-tracking. Real-time results show models like Claude Opus 5.5 and GPT-6.1 Sol reaching the end of part two.
2026-11-10 ~ 2026-11-10 · 2 related posts
- banteg launches a live Sokoban eval for LLMs — banteg · 2026-11-10
- Sokoban eval: Opus and Sol with a Python REPL outpace pure-thinking rivals — banteg · 2026-11-10