Playing With AI: How Do State-Of-The-Art Large Language Models Perform in the 1977 Text-Based Adventure Game Zork? — mentioned by hephaes7us

Mon, 13 Jul 2026 20:01:56 GMT

I've started playing with Zork-Bench.[1] I've been making tweaks to the runtime/harness and to the prompting. Currently, I have Qwen3.6-27b scoring up to ~50 points, which, according to the original paper [2], is comparable to the performance Claude Opus 4.5 showed on this task. I had Claude whip up a viewer, which I guess I can actually share. Some real sessions are here, if anyone's interested: https://zork-tmp.taf.codes/ It's a fun problem for thinking about agent/harness engineering generally. [1] https://github.com/mnky9800n/zork-bench [2] https://arxiv.org/abs/2602.15867

Paper and discussion history. A mention is not an endorsement.

Playing With AI: How Do State-Of-The-Art Large Language Models Perform in the 1977 Text-Based Adventure Game Zork? · HackerPapers discussions

Playing With AI: How Do State-Of-The-Art Large Language Models Perform in the 1977 Text-Based Adventure Game Zork? — mentioned by hephaes7us