LIBERO-90 task 26 · 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: 11m 22s; Task process wall time

Canonical catalog

Task definition

Model instruction: put the wine bottle in the bottom drawer of the cabinet
BDDL language: put the wine bottle in the bottom drawer of the cabinet
Problem: libero_kitchen_tabletop_manipulation
Objects: akita_black_bowl_1, wine_bottle_1
Fixtures: kitchen_table, white_cabinet_1, wine_rack_1
Initial-state predicates: 5
Fixed init states: 50

Exact initial-state predicates

(on akita_black_bowl_1 kitchen_table_akita_black_bowl_init_region)
(on wine_bottle_1 kitchen_table_wine_bottle_init_region)
(on white_cabinet_1 kitchen_table_white_cabinet_init_region)
(on wine_rack_1 kitchen_table_wine_rack_init_region)
(open white_cabinet_1_bottom_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.

wine bottle 1 is in white cabinet 1 bottom region
(in wine_bottle_1 white_cabinet_1_bottom_region)

Exact parsed BDDL goal state

(in wine_bottle_1 white_cabinet_1_bottom_region)

Selected rollout

LIBERO-90 · Task 026 · 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	273 KB
2	Failure	1001	1	400	137 KB
3	Failure	1002	2	400	218 KB
4	Failure	1003	3	400	259 KB
5	Failure	1004	4	400	176 KB
6	Failure	1005	5	400	224 KB
7	Failure	1006	6	400	407 KB
8	Failure	1007	7	400	282 KB
9	Failure	1008	8	400	172 KB
10	Success	1009	9	392	217 KB
11	Failure	1010	11	400	209 KB
12	Failure	1011	12	400	255 KB
13	Failure	1012	13	400	229 KB
14	Success	1013	14	238	141 KB
15	Failure	1014	16	400	318 KB
16	Failure	1015	17	400	345 KB
17	Failure	1016	18	400	201 KB
18	Failure	1017	19	400	207 KB
19	Failure	1018	20	400	242 KB
20	Failure	1019	21	400	291 KB
21	Failure	1020	22	400	211 KB
22	Failure	1021	23	400	250 KB
23	Failure	1022	24	400	262 KB
24	Failure	1023	25	400	304 KB
25	Failure	1024	26	400	289 KB
26	Failure	1025	27	400	260 KB
27	Failure	1026	28	400	218 KB
28	Success	1027	29	207	162 KB
29	Failure	1028	31	400	316 KB
30	Failure	1029	32	400	210 KB
31	Failure	1030	33	400	249 KB
32	Failure	1031	34	400	197 KB
33	Failure	1032	35	400	239 KB
34	Failure	1033	36	400	280 KB
35	Failure	1034	37	400	212 KB
36	Failure	1035	38	400	253 KB
37	Failure	1036	39	400	257 KB
38	Failure	1037	40	400	218 KB
39	Failure	1038	41	400	291 KB
40	Failure	1039	42	400	251 KB
41	Failure	1040	43	400	236 KB
42	Failure	1041	44	400	386 KB
43	Failure	1042	45	400	228 KB
44	Failure	1043	46	400	210 KB
45	Failure	1044	47	400	251 KB
46	Failure	1045	48	400	221 KB
47	Failure	1046	49	400	257 KB
48	Failure	1047	0	400	242 KB
49	Failure	1048	1	400	339 KB
50	Failure	1049	2	400	312 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 9:38 AM UTC
Manifest SHA-256: 91badf7e81…844d1077
Aggregate SHA-256: 15b2b5e320…cfe23965
Episode index SHA-256: 5b91e73c23…858a0989
Validation SHA-256: d940c2f2b6…f41ab433
Artifact inventory SHA-256: 8cb45bb4c5…609ec7a5