LIBERO-90 task 63 · MolmoAct 2 — LIBERO Evaluation Gallery

Canonical catalog

Task definition

Model instruction: stack the left bowl on the right bowl and place them in the tray
BDDL language: stack the left bowl on the right bowl and place them in the tray
Problem: libero_living_room_tabletop_manipulation
Objects: akita_black_bowl_1, akita_black_bowl_2, chocolate_pudding_1, new_salad_dressing_1, wooden_tray_1
Fixtures: living_room_table
Initial-state predicates: 5
Fixed init states: 50

Exact initial-state predicates

(on chocolate_pudding_1 living_room_table_chocolate_pudding_init_region)
(on akita_black_bowl_1 living_room_table_akita_black_bowl_left_init_region)
(on akita_black_bowl_2 living_room_table_akita_black_bowl_right_init_region)
(on new_salad_dressing_1 living_room_table_salad_dressing_init_region)
(on wooden_tray_1 living_room_table_wooden_tray_init_region)

Open exact BDDL definition

Simulator truth

Completion criteria

LIBERO checks these BDDL goal predicates after every action. All conditions must be true simultaneously in the same simulator step for the rollout to succeed.

akita black bowl 1 is on akita black bowl 2
(on akita_black_bowl_1 akita_black_bowl_2)
akita black bowl 2 is in wooden tray 1 contain region
(in akita_black_bowl_2 wooden_tray_1_contain_region)

Exact parsed BDDL goal state

(on akita_black_bowl_1 akita_black_bowl_2)
(in akita_black_bowl_2 wooden_tray_1_contain_region)

Selected rollout

LIBERO-90 · Task 063 · Episode 1

Failure

Agent view observation.images.image

Eye in hand observation.images.image2

Rollout record

Episode metadata

Link to episode

Episode: 1
Seed: 1000
Init state: 0
Control steps: 400
Wall time: 15s
Outcome: Failure

Evidence browser

All rollouts

Select one episode to mount only its two camera streams in the player.

Episode	Outcome	Seed	Init state	Steps	Video
1	Failure	1000	0	400	286 KB
2	Failure	1001	1	400	185 KB
3	Failure	1002	2	400	185 KB
4	Failure	1003	3	400	203 KB
5	Failure	1004	4	400	200 KB
6	Failure	1005	5	400	243 KB
7	Failure	1006	6	400	228 KB
8	Failure	1007	7	400	196 KB
9	Failure	1008	8	400	200 KB
10	Failure	1009	9	400	197 KB
11	Failure	1010	10	400	213 KB
12	Failure	1011	11	400	311 KB
13	Failure	1012	12	400	205 KB
14	Failure	1013	13	400	196 KB
15	Failure	1014	14	400	236 KB
16	Failure	1015	15	400	240 KB
17	Failure	1016	16	400	205 KB
18	Failure	1017	17	400	199 KB
19	Failure	1018	18	400	245 KB
20	Failure	1019	19	400	242 KB
21	Failure	1020	20	400	269 KB
22	Failure	1021	21	400	192 KB
23	Failure	1022	22	400	227 KB
24	Failure	1023	23	400	324 KB
25	Failure	1024	24	400	283 KB
26	Failure	1025	25	400	207 KB
27	Failure	1026	26	400	213 KB
28	Failure	1027	27	400	221 KB
29	Failure	1028	28	400	237 KB
30	Failure	1029	29	400	192 KB
31	Failure	1030	30	400	280 KB
32	Failure	1031	31	400	204 KB
33	Failure	1032	32	400	200 KB
34	Failure	1033	33	400	180 KB
35	Failure	1034	34	400	192 KB
36	Failure	1035	35	400	227 KB
37	Failure	1036	36	400	299 KB
38	Failure	1037	37	400	234 KB
39	Failure	1038	38	400	199 KB
40	Failure	1039	39	400	216 KB
41	Failure	1040	40	400	328 KB
42	Failure	1041	41	400	198 KB
43	Failure	1042	42	400	364 KB
44	Failure	1043	43	400	200 KB
45	Failure	1044	44	400	233 KB
46	Failure	1045	45	400	195 KB
47	Failure	1046	46	400	213 KB
48	Failure	1047	47	400	198 KB
49	Failure	1048	48	400	217 KB
50	Failure	1049	49	400	191 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 4:04 PM UTC
Manifest SHA-256: 2595959594…0eb18d17
Aggregate SHA-256: 257abb3760…0abd8a61
Episode index SHA-256: e124dac07b…6b872789
Validation SHA-256: 9d6f008861…3df94b4e
Artifact inventory SHA-256: 926b8ca2da…5c541d1a