LIBERO-90 task 52 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 8.0%; 4 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 12m 6s; Task process wall time

Canonical catalog

Task definition

Model instruction: pick up the milk and put it in the basket
BDDL language: pick up the milk 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.

milk 1 is in basket 1 contain region
(in milk_1 basket_1_contain_region)

Exact parsed BDDL goal state

(in milk_1 basket_1_contain_region)

Selected rollout

LIBERO-90 · Task 052 · 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	256 KB
2	Success	1001	1	376	237 KB
3	Failure	1002	3	400	257 KB
4	Success	1003	4	221	175 KB
5	Failure	1004	6	400	161 KB
6	Failure	1005	7	400	206 KB
7	Failure	1006	8	400	263 KB
8	Failure	1007	9	400	154 KB
9	Failure	1008	10	400	273 KB
10	Failure	1009	11	400	207 KB
11	Failure	1010	12	400	257 KB
12	Failure	1011	13	400	273 KB
13	Failure	1012	14	400	257 KB
14	Failure	1013	15	400	236 KB
15	Failure	1014	16	400	255 KB
16	Failure	1015	17	400	272 KB
17	Failure	1016	18	400	257 KB
18	Failure	1017	19	400	210 KB
19	Failure	1018	20	400	282 KB
20	Failure	1019	21	400	250 KB
21	Failure	1020	22	400	259 KB
22	Failure	1021	23	400	268 KB
23	Failure	1022	24	400	261 KB
24	Failure	1023	25	400	256 KB
25	Failure	1024	26	400	277 KB
26	Success	1025	27	109	87 KB
27	Failure	1026	29	400	260 KB
28	Failure	1027	30	400	270 KB
29	Failure	1028	31	400	186 KB
30	Success	1029	32	360	279 KB
31	Failure	1030	34	400	259 KB
32	Failure	1031	35	400	230 KB
33	Failure	1032	36	400	213 KB
34	Failure	1033	37	400	273 KB
35	Failure	1034	38	400	268 KB
36	Failure	1035	39	400	254 KB
37	Failure	1036	40	400	255 KB
38	Failure	1037	41	400	245 KB
39	Failure	1038	42	400	220 KB
40	Failure	1039	43	400	263 KB
41	Failure	1040	44	400	270 KB
42	Failure	1041	45	400	264 KB
43	Failure	1042	46	400	268 KB
44	Failure	1043	47	400	216 KB
45	Failure	1044	48	400	188 KB
46	Failure	1045	49	400	262 KB
47	Failure	1046	0	400	278 KB
48	Failure	1047	1	400	230 KB
49	Failure	1048	2	400	274 KB
50	Failure	1049	3	400	246 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 2:14 PM UTC
Manifest SHA-256: 869383a2d1…7328483a
Aggregate SHA-256: a3d484d54c…cb827853
Episode index SHA-256: 3797f086e2…21283109
Validation SHA-256: 4cd004a4a8…8c529b6f
Artifact inventory SHA-256: ddc4222e5d…8696f084