Interatomic potential modeling on Revised MD17 (val test) benchmark leaderboard · SOTA2 Research

Interatomic potential modeling on Revised MD17 (val test)

6.6Aspirin Force ErrorMACE

Evaluation Results

Method	Links
MACE2022.06		6.6	2.2	1.2	3	0.4	0.3	0.4	2.1	0.8	4.1	0.5	1.6	1.3	4.8	0.9	3.1	0.5	1.5	0.5	2.1
Allegro2022.06		7.3	2.3	1.2	2.6	0.3	0.2	0.4	2.1	0.6	3.6	0.2	0.9	1.5	4.9	0.9	2.9	0.4	1.8	0.6	1.8
NequIP2022.06		8.2	2.3	0.7	2.9	0.04	0.3	0.4	2.8	0.8	5.1	0.9	1.3	1.4	5.9	0.7	4	0.3	1.6	0.4	3.1
BOTNet2022.06		8.5	2.3	0.7	3.3	0.03	0.3	0.4	3.2	0.8	5.8	0.2	1.8	1.3	5.8	0.8	4.3	0.3	1.9	0.4	3.2
GemNet (T/Q)2022.06		9.5	—	—	—	—	0.5	—	3.6	—	6.6	—	1.9	—	—	—	5.3	—	2.2	—	3.8
NewtonNet2022.06		15.1	7.3	6.1	5.9	—	—	2.6	9.1	4.1	14	5.2	3.6	6.1	11.4	4.9	8.5	4.1	3.8	4.6	6.4
PaiNN2022.06		16.1	6.9	—	—	—	—	2.7	10	3.9	13.8	5.1	3.6	—	—	4.9	9.1	4.2	4.4	4.5	6.1
ACE2022.06		17.9	6.1	3.6	10.9	0.04	0.5	1.2	7.3	1.7	11.1	0.9	5.1	4	12.7	1.8	9.3	1.1	6.5	1.1	6.6
FCHL2022.06		20.9	6.2	2.8	10.8	0.35	2.6	0.9	6.2	1.5	10.3	1.2	6.5	2.9	12.3	1.8	9.5	1.7	8.8	0.6	4.2
DimeNet2022.06		21.6	8.8	—	—	3.4	8.1	2.8	10	4.5	16.6	5.3	9.3	—	—	5.8	16.2	4.4	9.4	5	13.1
ANI2022.06		40.6	16.6	15.9	35.4	3.3	10	2.5	13.4	4.6	24.5	11.3	29.2	11.5	30.4	9.2	29.7	7.7	24.3	5.1	21.4
MACE2022.06		43.9	17	5.4	17.7	0.7	2.7	6.7	32.6	10	43.3	2.1	9.2	9.7	31.5	6.5	28.4	3.1	12.1	4.4	25.9
GAP2022.06		44.9	17.7	8.5	24.5	0.75	6	3.5	18.1	4.8	26.4	3.8	16.5	8.5	28.9	5.6	24.7	4	17.8	3	17.6
NequIP2022.06		52	19.5	6	20	0.6	2.9	8.7	40.2	12.7	52.5	2.1	10	14.3	39.7	8	35	3.3	15.1	7.3	40.1
ACE2022.06		63.8	26.2	9	28.8	0.2	2.7	8.6	43	12.8	63.5	3.8	19.7	13.6	45.7	8.9	41.7	5.3	27.1	6.5	36.2