LIBERO-10 task 4 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 98.0%; 49 of 50

Control horizon: 520; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 9m 1s; Task process wall time

Canonical catalog

Task definition

Model instruction: put the white mug on the left plate and put the yellow and white mug on the right plate
BDDL language: put the white mug on the left plate and put the yellow and white mug on the right plate
Problem: libero_living_room_tabletop_manipulation
Objects: plate_1, plate_2, porcelain_mug_1, red_coffee_mug_1, white_yellow_mug_1
Fixtures: living_room_table
Initial-state predicates: 5
Fixed init states: 50

Exact initial-state predicates

(on plate_1 living_room_table_plate_left_region)
(on plate_2 living_room_table_plate_right_region)
(on red_coffee_mug_1 living_room_table_red_coffee_mug_init_region)
(on white_yellow_mug_1 living_room_table_white_yellow_mug_init_region)
(on porcelain_mug_1 living_room_table_porcelain_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.

porcelain mug 1 is on plate 1
(on porcelain_mug_1 plate_1)
white yellow mug 1 is on plate 2
(on white_yellow_mug_1 plate_2)

Exact parsed BDDL goal state

(on porcelain_mug_1 plate_1)
(on white_yellow_mug_1 plate_2)

Selected rollout

LIBERO-10 · Task 004 · 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: 214
Wall time: 11s
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	214	133 KB
2	Success	1001	2	225	139 KB
3	Success	1002	4	230	139 KB
4	Success	1003	6	225	134 KB
5	Success	1004	8	214	133 KB
6	Success	1005	10	203	125 KB
7	Success	1006	12	216	131 KB
8	Success	1007	14	215	133 KB
9	Success	1008	16	220	133 KB
10	Success	1009	18	228	132 KB
11	Success	1010	20	221	132 KB
12	Success	1011	22	210	129 KB
13	Success	1012	24	215	134 KB
14	Success	1013	26	206	126 KB
15	Success	1014	28	201	129 KB
16	Success	1015	30	229	137 KB
17	Success	1016	32	207	130 KB
18	Success	1017	34	218	131 KB
19	Success	1018	36	217	136 KB
20	Success	1019	38	225	139 KB
21	Success	1020	40	214	138 KB
22	Success	1021	42	221	135 KB
23	Failure	1022	44	520	204 KB
24	Success	1023	45	230	139 KB
25	Success	1024	47	214	132 KB
26	Success	1025	49	217	139 KB
27	Success	1026	1	214	139 KB
28	Success	1027	3	209	130 KB
29	Success	1028	5	229	141 KB
30	Success	1029	7	229	144 KB
31	Success	1030	9	218	135 KB
32	Success	1031	11	217	135 KB
33	Success	1032	13	210	131 KB
34	Success	1033	15	221	133 KB
35	Success	1034	17	214	139 KB
36	Success	1035	19	218	129 KB
37	Success	1036	21	202	129 KB
38	Success	1037	23	214	131 KB
39	Success	1038	25	206	130 KB
40	Success	1039	27	224	131 KB
41	Success	1040	29	220	133 KB
42	Success	1041	31	215	132 KB
43	Success	1042	33	225	141 KB
44	Success	1043	35	219	131 KB
45	Success	1044	37	231	134 KB
46	Success	1045	39	218	136 KB
47	Success	1046	41	228	138 KB
48	Success	1047	43	404	202 KB
49	Success	1048	45	232	137 KB
50	Success	1049	47	212	127 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 12:22 AM UTC
Manifest SHA-256: 98d2c3a30b…404f519d
Aggregate SHA-256: e1f77b095f…e6c6199b
Episode index SHA-256: d509ed837d…b50239f7
Validation SHA-256: 8e46b232ec…334f5b18
Artifact inventory SHA-256: 549d9630c2…25d56f5a