16 LLMs take on TIS-100 puzzle solving and optimization
What happened
Wincon tested 16 large language models on TIS-100's 55 puzzles, measuring both solving and program optimization. The evaluation produced 133 new Pareto-frontier points across 18 puzzles and broke 3 cycle-count records. Opus 5.5 and GPT-6 Astra each solved all 55 puzzles and found new frontier points on 11. The gap between the two in record proximity was not statistically significant. Every counted program was verified by real game replay and 100,000 tests. Community players later improved most of the programs.
Written by AI from the coverage · updated yesterday
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageLLMs Play Zachtronics' TIS-100
Wincon 在 TIS-100 的 55 道谜题上测试了 16 个大语言模型，在 18 道题中获得 133 个新的帕累托前沿点，并打破 3 项运行周期纪录。Opus 5.5 与 GPT-6 Astra 均解出全部 55 道题，各在 11 道题上找到新前沿点，两者的纪录接近度差异未达到统计显著水平。计入结果的程序均经过真实游戏重放及 100,000 次测试，社区玩家随后进一步优化了其中多数程序。
Heat over time
Heat now 5·Comparable peak 10（Nov 11 10:00）·Comparable change over 24 hours -50%
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.