DuelLab GameBench 2 evaluates AI-generated game-playing programs by compiling and running them head-to-head across an evolving set of named public board and strategy games. Public standings, methodology, and release data are available; the evaluator, engine implementation, and unpublished operational artifacts remain private. Category: Games & Game Agents. Imported rows: 34. Top imported result: Claude Fable 5, rank 1, 71.8.
Kimi K3 beats GPT 5.6 Sol in agentic knowledge work