Instruction-following robotic manipulation on CALVIN ABC→D (unseen environment D) benchmark leaderboard · SOTA2 Research

Instruction-following robotic manipulation on CALVIN ABC→D (unseen environment D)

98.5Success Rate (Length 1)HiF-VLA

Evaluation Results

Method	Links
HiF-VLA2025.12		98.5	94.1	88.1	81.4	73.1	4.35
RoboVLMs2025.12		98	93.6	85.4	77.8	70.4	4.25
PALM2026.01		96.9	93.8	89.3	85.9	82	4.48
VPP2025.12		96.5	90.9	86.6	82	76.9	4.33
OpenVLA-OFT2025.12		96.3	89.1	82.4	75.8	66.5	4.1
Seer2025.12		96.3	91.6	86.1	80.3	74	4.28
CLOVER2025.12		96	83.5	70.8	57.5	45.4	3.53
UniVLA2025.12		95.5	85.8	74.8	66.9	56.5	3.8
PALM (✗ progress)2026.01		95.3	85.6	79.5	74.3	67	4.02
Seer2026.01		94.4	87.2	79.9	72.2	64.3	3.98
RoboUniview2026.01		94.2	84.2	73.4	62.2	50.7	3.65
π02026.01		93.8	85	76.7	68.1	59.9	3.92
π02025.12		93.8	85	76.7	68.1	59.9	3.92
π02025.12		93.7	83.2	74	62.9	51	3.65
HiF-VLA2025.12		93.5	87.4	81.4	75.9	69.4	4.08
UP-VLA2025.12		92.8	86.5	81.5	76.9	69.9	4.08
3D Diffuser Actor2026.01		92.2	78.7	63.9	51.2	41.2	3.27
Vidman2025.12		91.5	76.4	68.2	59.2	46.7	3.42
OpenVLA2026.01		91.3	77.8	62	52.1	43.5	3.27
OpenVLA2025.12		91.3	77.8	62	52.1	43.5	3.27
VPP2025.12		90.9	81.5	71.3	62	51.8	3.58
Susie2026.01		87	69	49	38	26	2.69
SuSIE2025.12		87	69	49	38	26	2.69
GR-12026.01		85.4	71.2	59.6	49.7	40.1	3.06
GR-12025.12		85.4	71.2	59.6	49.7	40.1	3.06
Robo-Flamingo2026.01		82.4	61.9	46.6	33.1	23.5	2.47
RT-12026.01		53.3	22.2	9.4	3.8	1.3	0.9
3D-VLA2026.01		44.7	16.3	8.1	1.6	0	0.71
Diffusion Policy2026.01		40.2	12.3	2.6	0.8	0	0.56