Question Answering on ARC-E Small Shift (test) benchmark leaderboard · SOTA2 Research

Question Answering on ARC-E Small Shift (test)

78.9AccuracyBayesian-LoRA

Evaluation Results

Method	Links
Bayesian-LoRA2026.01		78.9	5.21	0.8
LA2026.01		78.5	3.1	0.62
LLLA2026.01		78.1	14.8	0.64
MAP2026.01		77.7	15.8	1.04
Ckpt Ens2026.01		77.4	12.1	0.8
Dropout2026.01		77.2	15.5	1.01
Temp2026.01		76.7	6.33	0.66
BLoB2026.01		76.3	5.48	0.6
BBB2026.01		75.8	13.4	0.79