{ "by_category": { "add-1d": { "correct": 65, "n": 71, "acc": 0.9155 }, "add-2d-carry": { "correct": 201, "n": 500, "acc": 0.402 }, "comparison": { "correct": 334, "n": 500, "acc": 0.668 }, "missing-addend": { "correct": 355, "n": 500, "acc": 0.71 }, "missing-factor": { "correct": 78, "n": 500, "acc": 0.156 }, "mul-1d": { "correct": 43, "n": 45, "acc": 0.9556 }, "mul-2dx1d": { "correct": 474, "n": 500, "acc": 0.948 }, "sub-borrow": { "correct": 433, "n": 500, "acc": 0.866 }, "two-step": { "correct": 285, "n": 500, "acc": 0.57 }, "which-bigger": { "correct": 278, "n": 300, "acc": 0.9267 } }, "runtime": "llama.cpp Q8_0 aggregate summary" }