LIBERO-90 task 66 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 6.0%; 3 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 11m 42s; Task process wall time

Canonical catalog

Task definition

Model instruction: put the red mug on the right plate
BDDL language: put the red 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.

red coffee mug 1 is on plate 2
(on red_coffee_mug_1 plate_2)

Exact parsed BDDL goal state

(on red_coffee_mug_1 plate_2)

Selected rollout

LIBERO-90 · Task 066 · 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	213 KB
2	Failure	1001	1	400	210 KB
3	Failure	1002	2	400	205 KB
4	Failure	1003	3	400	190 KB
5	Failure	1004	4	400	211 KB
6	Failure	1005	5	400	197 KB
7	Failure	1006	6	400	165 KB
8	Failure	1007	7	400	216 KB
9	Failure	1008	8	400	207 KB
10	Failure	1009	9	400	187 KB
11	Failure	1010	10	400	213 KB
12	Failure	1011	11	400	215 KB
13	Failure	1012	12	400	258 KB
14	Success	1013	13	145	97 KB
15	Failure	1014	15	400	196 KB
16	Failure	1015	16	400	222 KB
17	Failure	1016	17	400	197 KB
18	Failure	1017	18	400	205 KB
19	Failure	1018	19	400	203 KB
20	Failure	1019	20	400	219 KB
21	Failure	1020	21	400	233 KB
22	Failure	1021	22	400	216 KB
23	Failure	1022	23	400	182 KB
24	Failure	1023	24	400	208 KB
25	Failure	1024	25	400	203 KB
26	Failure	1025	26	400	181 KB
27	Failure	1026	27	400	204 KB
28	Failure	1027	28	400	189 KB
29	Failure	1028	29	400	206 KB
30	Failure	1029	30	400	155 KB
31	Failure	1030	31	400	200 KB
32	Failure	1031	32	400	208 KB
33	Failure	1032	33	400	207 KB
34	Failure	1033	34	400	201 KB
35	Failure	1034	35	400	211 KB
36	Failure	1035	36	400	191 KB
37	Success	1036	37	171	100 KB
38	Failure	1037	39	400	207 KB
39	Failure	1038	40	400	214 KB
40	Failure	1039	41	400	198 KB
41	Failure	1040	42	400	181 KB
42	Failure	1041	43	400	190 KB
43	Failure	1042	44	400	210 KB
44	Failure	1043	45	400	193 KB
45	Failure	1044	46	400	197 KB
46	Failure	1045	47	400	197 KB
47	Success	1046	48	86	60 KB
48	Failure	1047	0	400	205 KB
49	Failure	1048	1	400	203 KB
50	Failure	1049	2	400	197 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 4:41 PM UTC
Manifest SHA-256: e47ebf469b…d46f7e7d
Aggregate SHA-256: 45c483b45b…6b599091
Episode index SHA-256: ceebccdd94…fa4b46fc
Validation SHA-256: e1c7494dcf…f25120b7
Artifact inventory SHA-256: ced43b99d4…5fb55169