LIBERO-90 task 37 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 2.0%; 1 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 10m 53s; Task process wall time

Canonical catalog

Task definition

Model instruction: put the white bowl to the right of the plate
BDDL language: put the white bowl to the right of the plate
Problem: libero_kitchen_tabletop_manipulation
Objects: plate_1, white_bowl_1
Fixtures: kitchen_table, microwave_1
Initial-state predicates: 4
Fixed init states: 50

Exact initial-state predicates

(on white_bowl_1 microwave_1_top_side)
(on microwave_1 kitchen_table_microwave_init_region)
(close microwave_1)
(on plate_1 kitchen_table_plate_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.

white bowl 1 is on kitchen table plate right region
(on white_bowl_1 kitchen_table_plate_right_region)

Exact parsed BDDL goal state

(on white_bowl_1 kitchen_table_plate_right_region)

Selected rollout

LIBERO-90 · Task 037 · 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: 14s
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	257 KB
2	Failure	1001	1	400	263 KB
3	Failure	1002	2	400	314 KB
4	Failure	1003	3	400	217 KB
5	Failure	1004	4	400	306 KB
6	Failure	1005	5	400	245 KB
7	Failure	1006	6	400	281 KB
8	Failure	1007	7	400	236 KB
9	Failure	1008	8	400	293 KB
10	Failure	1009	9	400	227 KB
11	Failure	1010	10	400	233 KB
12	Failure	1011	11	400	155 KB
13	Failure	1012	12	400	274 KB
14	Failure	1013	13	400	268 KB
15	Failure	1014	14	400	295 KB
16	Failure	1015	15	400	243 KB
17	Failure	1016	16	400	242 KB
18	Failure	1017	17	400	164 KB
19	Failure	1018	18	400	300 KB
20	Failure	1019	19	400	262 KB
21	Failure	1020	20	400	277 KB
22	Failure	1021	21	400	212 KB
23	Failure	1022	22	400	179 KB
24	Failure	1023	23	400	236 KB
25	Failure	1024	24	400	243 KB
26	Failure	1025	25	400	275 KB
27	Failure	1026	26	400	297 KB
28	Failure	1027	27	400	287 KB
29	Failure	1028	28	400	259 KB
30	Failure	1029	29	400	270 KB
31	Failure	1030	30	400	267 KB
32	Failure	1031	31	400	159 KB
33	Failure	1032	32	400	275 KB
34	Failure	1033	33	400	261 KB
35	Failure	1034	34	400	301 KB
36	Success	1035	35	382	248 KB
37	Failure	1036	37	400	171 KB
38	Failure	1037	38	400	244 KB
39	Failure	1038	39	400	243 KB
40	Failure	1039	40	400	263 KB
41	Failure	1040	41	400	271 KB
42	Failure	1041	42	400	309 KB
43	Failure	1042	43	400	252 KB
44	Failure	1043	44	400	287 KB
45	Failure	1044	45	400	262 KB
46	Failure	1045	46	400	258 KB
47	Failure	1046	47	400	243 KB
48	Failure	1047	48	400	194 KB
49	Failure	1048	49	400	283 KB
50	Failure	1049	0	400	291 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 11:41 AM UTC
Manifest SHA-256: 7605842363…1f96215a
Aggregate SHA-256: 2715edaf81…a8d011b6
Episode index SHA-256: 0e8ce3339a…f026803b
Validation SHA-256: 953c2bd91e…f678533b
Artifact inventory SHA-256: 3b62b0f442…12ca975f