lm-evaluation-harness/tests/testdata/arc_challenge-v2.0-res.json

{"results": {"arc_challenge": {"acc": 0.26621160409556316, "acc_norm": 0.28242320819112626, "acc_norm_stderr": 0.01315545688409722, "acc_stderr": 0.01291577478152323}}, "versions": {"arc_challenge": "2.0"}}