LIBERO-90 task 77 · 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: 7m 37s; Task process wall time

Canonical catalog

Task definition

Model instruction: pick up the book and place it in the back compartment of the caddy
BDDL language: pick up the book and place it in the back compartment of the caddy
Problem: libero_study_tabletop_manipulation
Objects: black_book_1, red_coffee_mug_1
Fixtures: desk_caddy_1, study_table
Initial-state predicates: 3
Fixed init states: 50

Exact initial-state predicates

(on desk_caddy_1 study_table_desk_caddy_init_region)
(on black_book_1 study_table_black_book_init_region)
(on red_coffee_mug_1 study_table_red_coffee_mug_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.

black book 1 is in desk caddy 1 back contain region
(in black_book_1 desk_caddy_1_back_contain_region)

Exact parsed BDDL goal state

(in black_book_1 desk_caddy_1_back_contain_region)

Selected rollout

LIBERO-90 · Task 077 · 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	152 KB
2	Failure	1001	1	400	157 KB
3	Success	1002	2	124	70 KB
4	Failure	1003	4	400	171 KB
5	Success	1004	5	123	68 KB
6	Failure	1005	7	400	165 KB
7	Success	1006	8	118	63 KB
8	Success	1007	10	108	61 KB
9	Success	1008	12	113	61 KB
10	Success	1009	14	129	72 KB
11	Success	1010	16	114	61 KB
12	Failure	1011	18	400	157 KB
13	Failure	1012	19	400	179 KB
14	Success	1013	20	131	74 KB
15	Success	1014	22	116	67 KB
16	Failure	1015	24	400	147 KB
17	Failure	1016	25	400	146 KB
18	Failure	1017	26	400	169 KB
19	Failure	1018	27	400	149 KB
20	Success	1019	28	112	65 KB
21	Failure	1020	30	400	164 KB
22	Success	1021	31	138	79 KB
23	Failure	1022	33	400	162 KB
24	Failure	1023	34	400	177 KB
25	Failure	1024	35	400	162 KB
26	Failure	1025	36	400	180 KB
27	Success	1026	37	105	56 KB
28	Success	1027	39	116	68 KB
29	Failure	1028	41	400	165 KB
30	Success	1029	42	121	69 KB
31	Failure	1030	44	400	153 KB
32	Success	1031	45	126	72 KB
33	Failure	1032	47	400	162 KB
34	Failure	1033	48	400	130 KB
35	Success	1034	49	119	67 KB
36	Failure	1035	1	400	172 KB
37	Success	1036	2	122	70 KB
38	Failure	1037	4	400	162 KB
39	Success	1038	5	121	67 KB
40	Failure	1039	7	400	173 KB
41	Success	1040	8	123	64 KB
42	Success	1041	10	116	63 KB
43	Success	1042	12	129	66 KB
44	Success	1043	14	126	71 KB
45	Success	1044	16	139	72 KB
46	Failure	1045	18	400	172 KB
47	Failure	1046	19	400	176 KB
48	Success	1047	20	156	82 KB
49	Success	1048	22	118	68 KB
50	Success	1049	24	124	71 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 6:21 PM UTC
Manifest SHA-256: ea56ecbd05…868b2891
Aggregate SHA-256: 132ec09e8d…4d7d4bbe
Episode index SHA-256: 6569686e7a…a3454a49
Validation SHA-256: b3e21e85e9…48ab75b6
Artifact inventory SHA-256: 68231d678a…1cac8cc4