LIBERO-90 task 3 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 0.0%; 0 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 12m 5s; Task process wall time

Canonical catalog

Task definition

Model instruction: put the butter at the back in the top drawer of the cabinet and close it
BDDL language: put the butter at the back in the top drawer of the cabinet and close it
Problem: libero_kitchen_tabletop_manipulation
Objects: akita_black_bowl_1, butter_1, butter_2, chocolate_pudding_1
Fixtures: kitchen_table, wooden_cabinet_1
Initial-state predicates: 6
Fixed init states: 50

Exact initial-state predicates

(on akita_black_bowl_1 kitchen_table_akita_black_bowl_init_region)
(on butter_1 kitchen_table_butter_front_init_region)
(on butter_2 kitchen_table_butter_back_init_region)
(on chocolate_pudding_1 kitchen_table_chocolate_pudding_init_region)
(on wooden_cabinet_1 kitchen_table_wooden_cabinet_init_region)
(open wooden_cabinet_1_top_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.

butter 2 is in wooden cabinet 1 top region
(in butter_2 wooden_cabinet_1_top_region)
wooden cabinet 1 top region is closed
(close wooden_cabinet_1_top_region)

Exact parsed BDDL goal state

(in butter_2 wooden_cabinet_1_top_region)
(close wooden_cabinet_1_top_region)

Selected rollout

LIBERO-90 · Task 003 · 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	330 KB
2	Failure	1001	1	400	220 KB
3	Failure	1002	2	400	173 KB
4	Failure	1003	3	400	144 KB
5	Failure	1004	4	400	188 KB
6	Failure	1005	5	400	156 KB
7	Failure	1006	6	400	247 KB
8	Failure	1007	7	400	316 KB
9	Failure	1008	8	400	242 KB
10	Failure	1009	9	400	288 KB
11	Failure	1010	10	400	243 KB
12	Failure	1011	11	400	260 KB
13	Failure	1012	12	400	217 KB
14	Failure	1013	13	400	217 KB
15	Failure	1014	14	400	204 KB
16	Failure	1015	15	400	263 KB
17	Failure	1016	16	400	349 KB
18	Failure	1017	17	400	288 KB
19	Failure	1018	18	400	252 KB
20	Failure	1019	19	400	168 KB
21	Failure	1020	20	400	276 KB
22	Failure	1021	21	400	156 KB
23	Failure	1022	22	400	251 KB
24	Failure	1023	23	400	117 KB
25	Failure	1024	24	400	175 KB
26	Failure	1025	25	400	207 KB
27	Failure	1026	26	400	301 KB
28	Failure	1027	27	400	250 KB
29	Failure	1028	28	400	250 KB
30	Failure	1029	29	400	288 KB
31	Failure	1030	30	400	143 KB
32	Failure	1031	31	400	157 KB
33	Failure	1032	32	400	262 KB
34	Failure	1033	33	400	243 KB
35	Failure	1034	34	400	189 KB
36	Failure	1035	35	400	227 KB
37	Failure	1036	36	400	284 KB
38	Failure	1037	37	400	268 KB
39	Failure	1038	38	400	291 KB
40	Failure	1039	39	400	353 KB
41	Failure	1040	40	400	289 KB
42	Failure	1041	41	400	278 KB
43	Failure	1042	42	400	245 KB
44	Failure	1043	43	400	257 KB
45	Failure	1044	44	400	229 KB
46	Failure	1045	45	400	235 KB
47	Failure	1046	46	400	153 KB
48	Failure	1047	47	400	285 KB
49	Failure	1048	48	400	216 KB
50	Failure	1049	49	400	266 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 5:18 AM UTC
Manifest SHA-256: 1724eca144…0b3d666a
Aggregate SHA-256: 5c0cc8a0df…5fb2a218
Episode index SHA-256: 34dd545462…d08d2ea6
Validation SHA-256: 97a49cf51f…7cc69e03
Artifact inventory SHA-256: 946daf5f32…173a8ddf