LIBERO-90 task 6 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 10.0%; 5 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 10m 52s; Task process wall time

Canonical catalog

Task definition

Model instruction: open the bottom drawer of the cabinet
BDDL language: open the bottom drawer of the cabinet
Problem: libero_kitchen_tabletop_manipulation
Objects: akita_black_bowl_1, plate_1
Fixtures: kitchen_table, wooden_cabinet_1
Initial-state predicates: 3
Fixed init states: 50

Exact initial-state predicates

(on akita_black_bowl_1 kitchen_table_akita_black_bowl_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 bottom region is open
(open wooden_cabinet_1_bottom_region)

Exact parsed BDDL goal state

(open wooden_cabinet_1_bottom_region)

Selected rollout

LIBERO-90 · Task 006 · 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	237 KB
2	Failure	1001	1	400	139 KB
3	Failure	1002	2	400	256 KB
4	Failure	1003	3	400	221 KB
5	Failure	1004	4	400	144 KB
6	Failure	1005	5	400	156 KB
7	Failure	1006	6	400	223 KB
8	Success	1007	7	137	97 KB
9	Failure	1008	9	400	299 KB
10	Failure	1009	10	400	196 KB
11	Failure	1010	11	400	223 KB
12	Failure	1011	12	400	261 KB
13	Failure	1012	13	400	293 KB
14	Failure	1013	14	400	209 KB
15	Failure	1014	15	400	306 KB
16	Failure	1015	16	400	315 KB
17	Failure	1016	17	400	131 KB
18	Failure	1017	18	400	268 KB
19	Failure	1018	19	400	316 KB
20	Failure	1019	20	400	175 KB
21	Failure	1020	21	400	142 KB
22	Failure	1021	22	400	242 KB
23	Failure	1022	23	400	265 KB
24	Failure	1023	24	400	238 KB
25	Success	1024	25	131	110 KB
26	Failure	1025	27	400	132 KB
27	Failure	1026	28	400	315 KB
28	Failure	1027	29	400	267 KB
29	Success	1028	30	161	122 KB
30	Failure	1029	32	400	286 KB
31	Failure	1030	33	400	216 KB
32	Failure	1031	34	400	218 KB
33	Success	1032	35	132	107 KB
34	Failure	1033	37	400	180 KB
35	Failure	1034	38	400	143 KB
36	Failure	1035	39	400	252 KB
37	Failure	1036	40	400	267 KB
38	Failure	1037	41	400	301 KB
39	Failure	1038	42	400	274 KB
40	Failure	1039	43	400	211 KB
41	Failure	1040	44	400	293 KB
42	Failure	1041	45	400	141 KB
43	Failure	1042	46	400	301 KB
44	Failure	1043	47	400	328 KB
45	Success	1044	48	155	111 KB
46	Failure	1045	0	400	256 KB
47	Failure	1046	1	400	122 KB
48	Failure	1047	2	400	236 KB
49	Failure	1048	3	400	313 KB
50	Failure	1049	4	400	288 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 5:55 AM UTC
Manifest SHA-256: a513fbac7a…c343aaab
Aggregate SHA-256: f9203f1580…fc558b67
Episode index SHA-256: b170248daa…5e236f61
Validation SHA-256: c3e4c9d679…e83cc714
Artifact inventory SHA-256: b220f9b4d7…6c4b7e99