LIBERO-90 task 54 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 92.0%; 46 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 10m 8s; Task process wall time

Canonical catalog

Task definition

Model instruction: pick up the tomato sauce and put it in the basket
BDDL language: pick up the tomato sauce and put it in the basket
Problem: libero_living_room_tabletop_manipulation
Objects: alphabet_soup_1, basket_1, butter_1, cream_cheese_1, ketchup_1, milk_1, orange_juice_1, tomato_sauce_1
Fixtures: living_room_table
Initial-state predicates: 8
Fixed init states: 50

Exact initial-state predicates

(on alphabet_soup_1 living_room_table_alphabet_soup_init_region)
(on cream_cheese_1 living_room_table_cream_cheese_init_region)
(on tomato_sauce_1 living_room_table_tomato_sauce_init_region)
(on ketchup_1 living_room_table_ketchup_init_region)
(on milk_1 living_room_table_milk_init_region)
(on orange_juice_1 living_room_table_orange_juice_init_region)
(on butter_1 living_room_table_butter_init_region)
(on basket_1 living_room_table_basket_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.

tomato sauce 1 is in basket 1 contain region
(in tomato_sauce_1 basket_1_contain_region)

Exact parsed BDDL goal state

(in tomato_sauce_1 basket_1_contain_region)

Selected rollout

LIBERO-90 · Task 054 · Episode 1

Success

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: 302
Wall time: 14s
Outcome: Success

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	Success	1000	0	302	227 KB
2	Success	1001	2	249	190 KB
3	Success	1002	4	228	194 KB
4	Success	1003	6	228	186 KB
5	Success	1004	8	252	201 KB
6	Success	1005	10	249	192 KB
7	Success	1006	12	272	208 KB
8	Success	1007	14	238	187 KB
9	Success	1008	16	251	200 KB
10	Success	1009	18	240	196 KB
11	Success	1010	20	243	188 KB
12	Success	1011	22	351	243 KB
13	Success	1012	24	250	200 KB
14	Success	1013	26	233	180 KB
15	Success	1014	28	214	179 KB
16	Failure	1015	30	400	276 KB
17	Success	1016	31	253	209 KB
18	Success	1017	33	224	182 KB
19	Success	1018	35	345	227 KB
20	Success	1019	37	251	198 KB
21	Success	1020	39	275	223 KB
22	Success	1021	41	223	177 KB
23	Success	1022	43	266	208 KB
24	Success	1023	45	250	194 KB
25	Success	1024	47	251	211 KB
26	Success	1025	49	244	196 KB
27	Success	1026	1	236	184 KB
28	Success	1027	3	277	212 KB
29	Success	1028	5	247	196 KB
30	Success	1029	7	251	201 KB
31	Success	1030	9	244	196 KB
32	Success	1031	11	346	237 KB
33	Success	1032	13	253	207 KB
34	Success	1033	15	228	193 KB
35	Success	1034	17	240	185 KB
36	Success	1035	19	239	193 KB
37	Failure	1036	21	400	207 KB
38	Success	1037	22	304	218 KB
39	Success	1038	24	243	200 KB
40	Success	1039	26	233	179 KB
41	Success	1040	28	210	179 KB
42	Failure	1041	30	400	279 KB
43	Success	1042	31	246	197 KB
44	Success	1043	33	222	181 KB
45	Failure	1044	35	400	262 KB
46	Success	1045	36	334	223 KB
47	Success	1046	38	310	232 KB
48	Success	1047	40	229	181 KB
49	Success	1048	42	245	194 KB
50	Success	1049	44	253	207 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 2:36 PM UTC
Manifest SHA-256: be1dc061f7…3b9a9b48
Aggregate SHA-256: c8948bd601…7126754a
Episode index SHA-256: 9a21a39675…fd9c52f6
Validation SHA-256: a790a5cb90…a9d254b6
Artifact inventory SHA-256: 66906fc2c7…2000f27d