LIBERO-90 task 15 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 6.0%; 3 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 13m 10s; Task process wall time

Canonical catalog

Task definition

Model instruction: put the middle black bowl on top of the cabinet
BDDL language: put the middle black bowl on top of the cabinet
Problem: libero_kitchen_tabletop_manipulation
Objects: akita_black_bowl_1, akita_black_bowl_2, akita_black_bowl_3, plate_1
Fixtures: kitchen_table, wooden_cabinet_1
Initial-state predicates: 5
Fixed init states: 50

Exact initial-state predicates

(on akita_black_bowl_1 kitchen_table_akita_black_bowl_front_init_region)
(on akita_black_bowl_2 kitchen_table_akita_black_bowl_middle_init_region)
(on akita_black_bowl_3 kitchen_table_akita_black_bowl_back_init_region)
(on plate_1 kitchen_table_plate_init_region)
(on wooden_cabinet_1 kitchen_table_wooden_cabinet_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 wooden cabinet 1 top side
(on akita_black_bowl_2 wooden_cabinet_1_top_side)

Exact parsed BDDL goal state

(on akita_black_bowl_2 wooden_cabinet_1_top_side)

Selected rollout

LIBERO-90 · Task 015 · 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: 16s
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	389 KB
2	Failure	1001	1	400	431 KB
3	Failure	1002	2	400	395 KB
4	Failure	1003	3	400	435 KB
5	Failure	1004	4	400	376 KB
6	Failure	1005	5	400	441 KB
7	Failure	1006	6	400	483 KB
8	Failure	1007	7	400	425 KB
9	Failure	1008	8	400	406 KB
10	Failure	1009	9	400	490 KB
11	Failure	1010	10	400	412 KB
12	Failure	1011	11	400	247 KB
13	Failure	1012	12	400	396 KB
14	Failure	1013	13	400	396 KB
15	Failure	1014	14	400	396 KB
16	Failure	1015	15	400	365 KB
17	Failure	1016	16	400	452 KB
18	Failure	1017	17	400	380 KB
19	Failure	1018	18	400	478 KB
20	Success	1019	19	376	406 KB
21	Failure	1020	21	400	358 KB
22	Failure	1021	22	400	356 KB
23	Failure	1022	23	400	551 KB
24	Failure	1023	24	400	413 KB
25	Failure	1024	25	400	416 KB
26	Success	1025	26	246	296 KB
27	Failure	1026	28	400	423 KB
28	Success	1027	29	386	387 KB
29	Failure	1028	31	400	369 KB
30	Failure	1029	32	400	441 KB
31	Failure	1030	33	400	398 KB
32	Failure	1031	34	400	375 KB
33	Failure	1032	35	400	476 KB
34	Failure	1033	36	400	456 KB
35	Failure	1034	37	400	370 KB
36	Failure	1035	38	400	375 KB
37	Failure	1036	39	400	444 KB
38	Failure	1037	40	400	441 KB
39	Failure	1038	41	400	454 KB
40	Failure	1039	42	400	393 KB
41	Failure	1040	43	400	246 KB
42	Failure	1041	44	400	443 KB
43	Failure	1042	45	400	388 KB
44	Failure	1043	46	400	344 KB
45	Failure	1044	47	400	423 KB
46	Failure	1045	48	400	270 KB
47	Failure	1046	49	400	355 KB
48	Failure	1047	0	400	390 KB
49	Failure	1048	1	400	473 KB
50	Failure	1049	2	400	454 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 7:36 AM UTC
Manifest SHA-256: 3a08f099f8…acf6748c
Aggregate SHA-256: 74b218771b…a50f6c3c
Episode index SHA-256: 6907a0bbb2…c0c0e91a
Validation SHA-256: 26076061a4…0b56f612
Artifact inventory SHA-256: 434cd076f5…90901695