LIBERO-90 task 64 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 48.0%; 24 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 11m 21s; Task process wall time

Canonical catalog

Task definition

Model instruction: stack the right bowl on the left bowl and place them in the tray
BDDL language: stack the right bowl on the left 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 2 is on akita black bowl 1
(on akita_black_bowl_2 akita_black_bowl_1)
akita black bowl 1 is in wooden tray 1 contain region
(in akita_black_bowl_1 wooden_tray_1_contain_region)

Exact parsed BDDL goal state

(on akita_black_bowl_2 akita_black_bowl_1)
(in akita_black_bowl_1 wooden_tray_1_contain_region)

Selected rollout

LIBERO-90 · Task 064 · 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	344 KB
2	Success	1001	1	356	288 KB
3	Success	1002	3	317	248 KB
4	Failure	1003	5	400	250 KB
5	Success	1004	6	376	287 KB
6	Failure	1005	8	400	318 KB
7	Failure	1006	9	400	202 KB
8	Success	1007	10	246	232 KB
9	Success	1008	12	287	231 KB
10	Success	1009	14	237	217 KB
11	Failure	1010	16	400	299 KB
12	Failure	1011	17	400	296 KB
13	Failure	1012	18	400	292 KB
14	Success	1013	19	243	224 KB
15	Success	1014	21	255	241 KB
16	Failure	1015	23	400	346 KB
17	Failure	1016	24	400	208 KB
18	Success	1017	25	294	245 KB
19	Failure	1018	27	400	215 KB
20	Failure	1019	28	400	275 KB
21	Failure	1020	29	400	309 KB
22	Success	1021	30	243	228 KB
23	Failure	1022	32	400	302 KB
24	Failure	1023	33	400	251 KB
25	Success	1024	34	366	265 KB
26	Failure	1025	36	400	226 KB
27	Success	1026	37	383	323 KB
28	Failure	1027	39	400	312 KB
29	Failure	1028	40	400	325 KB
30	Failure	1029	41	400	318 KB
31	Failure	1030	42	400	270 KB
32	Failure	1031	43	400	297 KB
33	Success	1032	44	254	224 KB
34	Failure	1033	46	400	271 KB
35	Success	1034	47	303	267 KB
36	Success	1035	49	300	247 KB
37	Failure	1036	1	400	322 KB
38	Success	1037	2	256	235 KB
39	Failure	1038	4	400	296 KB
40	Failure	1039	5	400	199 KB
41	Failure	1040	6	400	324 KB
42	Failure	1041	7	400	307 KB
43	Success	1042	8	255	225 KB
44	Success	1043	10	331	299 KB
45	Success	1044	12	335	292 KB
46	Success	1045	14	231	213 KB
47	Success	1046	16	259	229 KB
48	Success	1047	18	266	251 KB
49	Success	1048	20	246	218 KB
50	Success	1049	22	228	215 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 4:16 PM UTC
Manifest SHA-256: 5520871b64…8d907551
Aggregate SHA-256: d7dfbddd86…33b774f5
Episode index SHA-256: 57e3bb382b…d5036cbf
Validation SHA-256: b0b3047428…5e3ba566
Artifact inventory SHA-256: ab6e54d2ad…bb8576f9