LIBERO-90 task 29 · MolmoAct 2 — LIBERO Evaluation Gallery

Completed task success rate: 10.0%; 5 of 50

Control horizon: 400; Maximum steps

Camera videos: 100; Two per rollout

Evaluation time: 11m 37s; Task process wall time

Canonical catalog

Task definition

Model instruction: put the black bowl in the top drawer of the cabinet
BDDL language: put the black bowl in the top drawer of the cabinet
Problem: libero_kitchen_tabletop_manipulation
Objects: akita_black_bowl_1, ketchup_1, plate_1
Fixtures: kitchen_table, white_cabinet_1
Initial-state predicates: 5
Fixed init states: 50

Exact initial-state predicates

(on akita_black_bowl_1 kitchen_table_akita_black_bowl_init_region)
(on plate_1 kitchen_table_plate_init_region)
(on white_cabinet_1 kitchen_table_white_cabinet_init_region)
(on ketchup_1 kitchen_table_ketchup_init_region)
(open white_cabinet_1_top_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.

akita black bowl 1 is in white cabinet 1 top region
(in akita_black_bowl_1 white_cabinet_1_top_region)

Exact parsed BDDL goal state

(in akita_black_bowl_1 white_cabinet_1_top_region)

Selected rollout

LIBERO-90 · Task 029 · 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	345 KB
2	Success	1001	1	149	163 KB
3	Failure	1002	3	400	311 KB
4	Failure	1003	4	400	313 KB
5	Failure	1004	5	400	350 KB
6	Failure	1005	6	400	333 KB
7	Failure	1006	7	400	311 KB
8	Failure	1007	8	400	374 KB
9	Success	1008	9	113	104 KB
10	Failure	1009	11	400	345 KB
11	Failure	1010	12	400	306 KB
12	Failure	1011	13	400	341 KB
13	Failure	1012	14	400	326 KB
14	Failure	1013	15	400	314 KB
15	Failure	1014	16	400	342 KB
16	Success	1015	17	120	119 KB
17	Failure	1016	19	400	301 KB
18	Failure	1017	20	400	317 KB
19	Failure	1018	21	400	409 KB
20	Failure	1019	22	400	318 KB
21	Failure	1020	23	400	313 KB
22	Failure	1021	24	400	307 KB
23	Failure	1022	25	400	395 KB
24	Failure	1023	26	400	339 KB
25	Failure	1024	27	400	313 KB
26	Success	1025	28	113	116 KB
27	Failure	1026	30	400	371 KB
28	Failure	1027	31	400	232 KB
29	Failure	1028	32	400	325 KB
30	Failure	1029	33	400	281 KB
31	Failure	1030	34	400	365 KB
32	Failure	1031	35	400	292 KB
33	Failure	1032	36	400	318 KB
34	Failure	1033	37	400	318 KB
35	Failure	1034	38	400	331 KB
36	Failure	1035	39	400	366 KB
37	Failure	1036	40	400	319 KB
38	Failure	1037	41	400	334 KB
39	Failure	1038	42	400	314 KB
40	Failure	1039	43	400	346 KB
41	Failure	1040	44	400	294 KB
42	Failure	1041	45	400	326 KB
43	Failure	1042	46	400	333 KB
44	Failure	1043	47	400	259 KB
45	Failure	1044	48	400	332 KB
46	Failure	1045	49	400	330 KB
47	Failure	1046	0	400	360 KB
48	Success	1047	1	153	155 KB
49	Failure	1048	3	400	300 KB
50	Failure	1049	4	400	339 KB

Integrity

Task attestation

Status: complete
Completed: Aug 16, 2026, 10:12 AM UTC
Manifest SHA-256: 2a68e20b07…3bd0125b
Aggregate SHA-256: b0b175a2f0…740af72d
Episode index SHA-256: ae2fcc4d19…ef75c0c1
Validation SHA-256: aa41d4f436…36fd919d
Artifact inventory SHA-256: fccf86eff6…ae77aae0