LIBERO-90 task 22 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 52.0%; 26 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 9m 47s; Task process wall time

Canonical catalog

Task definition

Model instruction: close the bottom drawer of the cabinet
BDDL language: close 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.

white cabinet 1 bottom region is closed
(close white_cabinet_1_bottom_region)

Exact parsed BDDL goal state

(close white_cabinet_1_bottom_region)

Selected rollout

LIBERO-90 · Task 022 · Episode 1

Success

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: 339
Wall time: 14s
Outcome: Success

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	Success	1000	0	339	193 KB
2	Success	1001	2	227	197 KB
3	Failure	1002	4	400	128 KB
4	Success	1003	5	136	109 KB
5	Failure	1004	7	400	185 KB
6	Failure	1005	8	400	183 KB
7	Success	1006	9	275	223 KB
8	Success	1007	11	214	208 KB
9	Success	1008	13	260	217 KB
10	Failure	1009	15	400	142 KB
11	Success	1010	16	223	214 KB
12	Success	1011	18	315	159 KB
13	Failure	1012	20	400	173 KB
14	Success	1013	21	234	128 KB
15	Failure	1014	23	400	196 KB
16	Failure	1015	24	400	276 KB
17	Success	1016	25	205	197 KB
18	Success	1017	27	247	213 KB
19	Failure	1018	29	400	151 KB
20	Failure	1019	30	400	166 KB
21	Success	1020	31	223	207 KB
22	Failure	1021	33	400	200 KB
23	Failure	1022	34	400	151 KB
24	Failure	1023	35	400	158 KB
25	Success	1024	36	230	206 KB
26	Failure	1025	38	400	284 KB
27	Success	1026	39	295	161 KB
28	Failure	1027	41	400	231 KB
29	Success	1028	42	239	214 KB
30	Success	1029	44	212	192 KB
31	Failure	1030	46	400	165 KB
32	Success	1031	47	94	104 KB
33	Success	1032	49	106	107 KB
34	Failure	1033	1	400	151 KB
35	Success	1034	2	267	217 KB
36	Failure	1035	4	400	128 KB
37	Success	1036	5	158	115 KB
38	Failure	1037	7	400	182 KB
39	Failure	1038	8	400	156 KB
40	Success	1039	9	215	201 KB
41	Failure	1040	11	400	218 KB
42	Success	1041	12	228	199 KB
43	Success	1042	14	382	204 KB
44	Success	1043	16	223	132 KB
45	Failure	1044	18	400	237 KB
46	Failure	1045	19	400	136 KB
47	Failure	1046	20	400	141 KB
48	Success	1047	21	259	148 KB
49	Failure	1048	23	400	192 KB
50	Success	1049	24	346	158 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 8:55 AM UTC
Manifest SHA-256: b242146e4f…ee6d37a4
Aggregate SHA-256: 6717809c64…5623e0a2
Episode index SHA-256: ee8485278f…cfd5518c
Validation SHA-256: a9d4eb58f7…03e2df5d
Artifact inventory SHA-256: 386c5bee64…a8ee09d7