MolmoAct 2 Evaluation gallery
IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Paper protocol Task 002 Validated task

put the wine bottle on top of the cabinet

BDDL language: put the wine bottle on the top of the drawer

Completed task success rate
94.0%
47 of 50
Control horizon
300
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
5m 18s
Task process wall time

Canonical catalog

Task definition

Model instruction
put the wine bottle on top of the cabinet
BDDL language
put the wine bottle on the top of the drawer
Problem
libero_tabletop_manipulation
Objects
akita_black_bowl_1, cream_cheese_1, plate_1, wine_bottle_1
Fixtures
flat_stove_1, main_table, wine_rack_1, wooden_cabinet_1
Initial-state predicates
7
Fixed init states
50
Exact initial-state predicates 
(on wine_bottle_1 main_table_wine_bottle_region)
(on akita_black_bowl_1 main_table_akita_black_bowl_region)
(on plate_1 main_table_plate_region)
(on cream_cheese_1 main_table_cream_cheese_region)
(on wooden_cabinet_1 main_table_cabinet_region)
(on flat_stove_1 main_table_stove_region)
(on wine_rack_1 main_table_wine_rack_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.

  1. wine bottle 1 is on wooden cabinet 1 top side

    (on wine_bottle_1 wooden_cabinet_1_top_side)
Exact parsed BDDL goal state 
(on wine_bottle_1 wooden_cabinet_1_top_side)

Selected rollout

LIBERO-Goal · Task 002 · Episode 1

Success
Agent view observation.images.image
Eye in hand observation.images.image2
Videos are not loaded yet.

Rollout record

Episode metadata

Link to episode
Episode
1
Seed
1000
Init state
0
Control steps
82
Wall time
6.8s
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 82 85 KB
2 Success 1001 2 84 83 KB
3 Success 1002 4 77 73 KB
4 Success 1003 6 96 88 KB
5 Success 1004 8 90 91 KB
6 Success 1005 10 76 75 KB
7 Success 1006 12 90 85 KB
8 Success 1007 14 86 81 KB
9 Success 1008 16 97 88 KB
10 Success 1009 18 90 86 KB
11 Success 1010 20 87 88 KB
12 Success 1011 22 102 91 KB
13 Success 1012 24 99 92 KB
14 Success 1013 26 87 82 KB
15 Success 1014 28 92 90 KB
16 Success 1015 30 83 80 KB
17 Success 1016 32 77 75 KB
18 Success 1017 34 86 84 KB
19 Success 1018 36 88 81 KB
20 Success 1019 38 83 80 KB
21 Success 1020 40 75 76 KB
22 Success 1021 42 83 82 KB
23 Success 1022 44 86 81 KB
24 Failure 1023 46 300 198 KB
25 Failure 1024 47 300 148 KB
26 Success 1025 48 86 82 KB
27 Success 1026 0 75 78 KB
28 Success 1027 2 83 84 KB
29 Success 1028 4 77 75 KB
30 Success 1029 6 100 90 KB
31 Success 1030 8 82 85 KB
32 Success 1031 10 78 78 KB
33 Success 1032 12 94 88 KB
34 Success 1033 14 88 84 KB
35 Failure 1034 16 300 169 KB
36 Success 1035 17 82 79 KB
37 Success 1036 19 79 74 KB
38 Success 1037 21 79 80 KB
39 Success 1038 23 87 86 KB
40 Success 1039 25 85 78 KB
41 Success 1040 27 82 79 KB
42 Success 1041 29 85 78 KB
43 Success 1042 31 86 87 KB
44 Success 1043 33 90 87 KB
45 Success 1044 35 96 89 KB
46 Success 1045 37 97 92 KB
47 Success 1046 39 86 84 KB
48 Success 1047 41 81 83 KB
49 Success 1048 43 90 89 KB
50 Success 1049 45 89 78 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 1:29 AM UTC
Manifest SHA-256
2dfdfa98aa…c4a251a9
Aggregate SHA-256
e2113e47ae…cf7e76bf
Episode index SHA-256
0aee5da70c…79bcb6a9
Validation SHA-256
aa4d14bc02…33d36372
Artifact inventory SHA-256
2845cc4227…3dee3cec