LIBERO-90 task 23 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 0.0%; 0 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 11m 33s; Task process wall time

Canonical catalog

Task definition

Model instruction: close the bottom drawer of the cabinet and open the top drawer
BDDL language: close the bottom drawer of the cabinet and open the top drawer
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)
white cabinet 1 top region is open
(open white_cabinet_1_top_region)

Exact parsed BDDL goal state

(close white_cabinet_1_bottom_region)
(open white_cabinet_1_top_region)

Selected rollout

LIBERO-90 · Task 023 · 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	188 KB
2	Failure	1001	1	400	203 KB
3	Failure	1002	2	400	234 KB
4	Failure	1003	3	400	243 KB
5	Failure	1004	4	400	215 KB
6	Failure	1005	5	400	136 KB
7	Failure	1006	6	400	207 KB
8	Failure	1007	7	400	204 KB
9	Failure	1008	8	400	272 KB
10	Failure	1009	9	400	241 KB
11	Failure	1010	10	400	240 KB
12	Failure	1011	11	400	227 KB
13	Failure	1012	12	400	253 KB
14	Failure	1013	13	400	185 KB
15	Failure	1014	14	400	261 KB
16	Failure	1015	15	400	174 KB
17	Failure	1016	16	400	156 KB
18	Failure	1017	17	400	243 KB
19	Failure	1018	18	400	216 KB
20	Failure	1019	19	400	196 KB
21	Failure	1020	20	400	266 KB
22	Failure	1021	21	400	252 KB
23	Failure	1022	22	400	203 KB
24	Failure	1023	23	400	240 KB
25	Failure	1024	24	400	248 KB
26	Failure	1025	25	400	148 KB
27	Failure	1026	26	400	203 KB
28	Failure	1027	27	400	189 KB
29	Failure	1028	28	400	258 KB
30	Failure	1029	29	400	158 KB
31	Failure	1030	30	400	147 KB
32	Failure	1031	31	400	150 KB
33	Failure	1032	32	400	205 KB
34	Failure	1033	33	400	201 KB
35	Failure	1034	34	400	246 KB
36	Failure	1035	35	400	257 KB
37	Failure	1036	36	400	219 KB
38	Failure	1037	37	400	253 KB
39	Failure	1038	38	400	203 KB
40	Failure	1039	39	400	223 KB
41	Failure	1040	40	400	245 KB
42	Failure	1041	41	400	246 KB
43	Failure	1042	42	400	138 KB
44	Failure	1043	43	400	262 KB
45	Failure	1044	44	400	200 KB
46	Failure	1045	45	400	246 KB
47	Failure	1046	46	400	239 KB
48	Failure	1047	47	400	257 KB
49	Failure	1048	48	400	255 KB
50	Failure	1049	49	400	195 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 9:07 AM UTC
Manifest SHA-256: d9590e4197…ee89736e
Aggregate SHA-256: 5fdc39dcd5…ef010ca8
Episode index SHA-256: 3bb59ec7a6…1e158f90
Validation SHA-256: 1511c4abde…d0143c82
Artifact inventory SHA-256: 9c9986f36a…f205a593