LIBERO-90 task 88 · 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: 10m 4s; Task process wall time

Canonical catalog

Task definition

Model instruction: pick up the book on the right and place it on the cabinet shelf
BDDL language: pick up the book on the right and place it on the cabinet shelf
Problem: libero_study_tabletop_manipulation
Objects: black_book_1, yellow_book_1, yellow_book_2
Fixtures: study_table, wooden_two_layer_shelf_1
Initial-state predicates: 4
Fixed init states: 50

Exact initial-state predicates

(on wooden_two_layer_shelf_1 study_table_wooden_two_layer_shelf_init_region)
(on yellow_book_1 study_table_yellow_book_right_init_region)
(on yellow_book_2 study_table_yellow_book_left_init_region)
(on black_book_1 study_table_black_book_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.

yellow book 1 is in wooden two layer shelf 1 top region
(in yellow_book_1 wooden_two_layer_shelf_1_top_region)

Exact parsed BDDL goal state

(in yellow_book_1 wooden_two_layer_shelf_1_top_region)

Selected rollout

LIBERO-90 · Task 088 · 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: 13s
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	190 KB
2	Failure	1001	1	400	241 KB
3	Failure	1002	2	400	217 KB
4	Failure	1003	3	400	169 KB
5	Failure	1004	4	400	240 KB
6	Failure	1005	5	400	230 KB
7	Failure	1006	6	400	186 KB
8	Failure	1007	7	400	185 KB
9	Failure	1008	8	400	224 KB
10	Failure	1009	9	400	213 KB
11	Failure	1010	10	400	206 KB
12	Failure	1011	11	400	183 KB
13	Failure	1012	12	400	223 KB
14	Failure	1013	13	400	194 KB
15	Failure	1014	14	400	228 KB
16	Failure	1015	15	400	219 KB
17	Failure	1016	16	400	236 KB
18	Failure	1017	17	400	241 KB
19	Failure	1018	18	400	238 KB
20	Failure	1019	19	400	199 KB
21	Failure	1020	20	400	160 KB
22	Failure	1021	21	400	187 KB
23	Failure	1022	22	400	226 KB
24	Failure	1023	23	400	246 KB
25	Failure	1024	24	400	197 KB
26	Failure	1025	25	400	210 KB
27	Failure	1026	26	400	190 KB
28	Failure	1027	27	400	200 KB
29	Failure	1028	28	400	230 KB
30	Failure	1029	29	400	220 KB
31	Failure	1030	30	400	210 KB
32	Failure	1031	31	400	210 KB
33	Failure	1032	32	400	199 KB
34	Failure	1033	33	400	222 KB
35	Failure	1034	34	400	212 KB
36	Failure	1035	35	400	222 KB
37	Failure	1036	36	400	259 KB
38	Failure	1037	37	400	183 KB
39	Failure	1038	38	400	224 KB
40	Failure	1039	39	400	207 KB
41	Failure	1040	40	400	210 KB
42	Failure	1041	41	400	155 KB
43	Failure	1042	42	400	204 KB
44	Failure	1043	43	400	202 KB
45	Failure	1044	44	400	200 KB
46	Failure	1045	45	400	203 KB
47	Failure	1046	46	400	238 KB
48	Failure	1047	47	400	227 KB
49	Failure	1048	48	400	249 KB
50	Failure	1049	49	400	194 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 8:21 PM UTC
Manifest SHA-256: ba327bae75…b8995e3b
Aggregate SHA-256: 03b5f2a875…1da74d52
Episode index SHA-256: 038c8ccca4…0eb3cccd
Validation SHA-256: 5e2dda377e…10713837
Artifact inventory SHA-256: 3e27c7b961…a86671a9