Model Editing on CounterFact (Comprehensive Evaluation) benchmark leaderboard · SOTA2 Research

Model Editing on CounterFact (Comprehensive Evaluation)

79.4ReliabilityCrispEdit

Evaluation Results

Method	Links
CrispEdit2026.02		79.4	55.9	69.3	67.5	49.5	54	76.5
AlphaEdit2026.02		74.9	57	47.4	32.9	41.5	40.5	37.5
CrispEdit-Seq2026.02		66.5	43.8	67.9	68.5	56.6	54	73
LocBF-FT2026.02		61.1	41.6	69.4	65	51.3	52.5	74
AlphaEdit2026.02		50.5	44.1	47.4	32.9	41.5	40.5	37.5
CrispEdit-Seq2026.02		39.1	29.2	67.9	68.5	56.6	54	73
CrispEdit2026.02		38.4	32.4	69.3	67.5	49.5	54	76.5
Adam-NSCL2026.02		19.1	8.5	68.6	22.8	57.1	39.5	16.5
FT Sequential2026.02		19.1	10.6	33.4	20.4	51.3	31.5	0
UltraEdit2026.02		18.1	12.4	69.2	68.6	49.2	52	74
LoRA2026.02		13.2	8.3	68.2	68.8	53.4	53	71
FT2026.02		12.3	6	67.4	22.7	50.4	40	18
LocBF-FT2026.02		10.9	13.3	69.4	65	51.3	52.5	74
UltraEdit2026.02		10.2	9.3	69.2	68.6	49.2	52	74
LoRA2026.02		9.5	2.7	68.2	68.8	53.4	53	71
LoRA Sequential2026.02		6.5	4.8	67.3	62.4	53.9	40	71
Adam-NSCL2026.02		1.7	1.8	68.6	22.8	57.1	39.5	16.5
FT2026.02		1.6	2.2	67.4	22.7	50.4	40	18
LoRA Sequential2026.02		1.6	2	67.3	62.4	53.9	40	71
FT Sequential2026.02		1.3	2.2	33.4	20.4	51.3	31.5	0
LLaMA-3-8B-Instruct2026.02		1.2	1	69.5	69.3	50.7	58	73.5
LLaMA-3-8B-Instruct2026.02		0.3	0.6	69.5	69.3	50.7	58	73.5
MEMIT2026.02		0	0	24.6	18.6	49.6	21	0
MEMIT2026.02		0	0	24.6	18.6	49.6	21	0
MEND2026.02		0	0	22.9	18.2	0	26	0
MEND2026.02		0	0	22.9	18.2	0	26	0