LIBERO-90 task 11 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 12.0%; 6 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 12m 9s; Task process wall time

Canonical catalog

Task definition

Model instruction: open the top drawer of the cabinet
BDDL language: open the top drawer 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.

wooden cabinet 1 top region is open
(open wooden_cabinet_1_top_region)

Exact parsed BDDL goal state

(open wooden_cabinet_1_top_region)

Selected rollout

LIBERO-90 · Task 011 · 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: 17s
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	268 KB
2	Failure	1001	1	400	210 KB
3	Failure	1002	2	400	261 KB
4	Failure	1003	3	400	276 KB
5	Failure	1004	4	400	325 KB
6	Failure	1005	5	400	259 KB
7	Failure	1006	6	400	222 KB
8	Failure	1007	7	400	187 KB
9	Failure	1008	8	400	258 KB
10	Failure	1009	9	400	246 KB
11	Success	1010	10	90	67 KB
12	Failure	1011	12	400	290 KB
13	Failure	1012	13	400	186 KB
14	Failure	1013	14	400	277 KB
15	Failure	1014	15	400	200 KB
16	Failure	1015	16	400	222 KB
17	Failure	1016	17	400	209 KB
18	Failure	1017	18	400	307 KB
19	Success	1018	19	90	66 KB
20	Failure	1019	21	400	144 KB
21	Failure	1020	22	400	145 KB
22	Failure	1021	23	400	184 KB
23	Failure	1022	24	400	209 KB
24	Failure	1023	25	400	243 KB
25	Failure	1024	26	400	241 KB
26	Failure	1025	27	400	262 KB
27	Failure	1026	28	400	215 KB
28	Failure	1027	29	400	272 KB
29	Failure	1028	30	400	341 KB
30	Failure	1029	31	400	285 KB
31	Failure	1030	32	400	189 KB
32	Failure	1031	33	400	208 KB
33	Failure	1032	34	400	288 KB
34	Failure	1033	35	400	268 KB
35	Failure	1034	36	400	254 KB
36	Failure	1035	37	400	216 KB
37	Failure	1036	38	400	223 KB
38	Success	1037	39	90	65 KB
39	Success	1038	41	86	63 KB
40	Failure	1039	43	400	275 KB
41	Failure	1040	44	400	228 KB
42	Success	1041	45	94	69 KB
43	Failure	1042	47	400	180 KB
44	Failure	1043	48	400	176 KB
45	Failure	1044	49	400	241 KB
46	Failure	1045	0	400	241 KB
47	Success	1046	1	91	66 KB
48	Failure	1047	3	400	243 KB
49	Failure	1048	4	400	271 KB
50	Failure	1049	5	400	262 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 6:44 AM UTC
Manifest SHA-256: 154b0e17c4…75400494
Aggregate SHA-256: 643ae58938…f9491df9
Episode index SHA-256: 73872c8d02…4a30b1dc
Validation SHA-256: 94acdf8c83…a882a036
Artifact inventory SHA-256: 3341535fca…f82bbf7a