MolmoAct 2 Evaluation gallery
IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Supplemental Task 061 Validated task

pick up the chocolate pudding and put it in the tray

Completed task success rate
100.0%
50 of 50
Control horizon
400
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
6m 31s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the chocolate pudding and put it in the tray
BDDL language
pick up the chocolate pudding and put it in the tray
Problem
libero_living_room_tabletop_manipulation
Objects
akita_black_bowl_1, akita_black_bowl_2, chocolate_pudding_1, new_salad_dressing_1, wooden_tray_1
Fixtures
living_room_table
Initial-state predicates
5
Fixed init states
50
Exact initial-state predicates 
(on chocolate_pudding_1 living_room_table_chocolate_pudding_init_region)
(on akita_black_bowl_1 living_room_table_akita_black_bowl_left_init_region)
(on akita_black_bowl_2 living_room_table_akita_black_bowl_right_init_region)
(on new_salad_dressing_1 living_room_table_salad_dressing_init_region)
(on wooden_tray_1 living_room_table_wooden_tray_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.

  1. chocolate pudding 1 is in wooden tray 1 contain region

    (in chocolate_pudding_1 wooden_tray_1_contain_region)
Exact parsed BDDL goal state 
(in chocolate_pudding_1 wooden_tray_1_contain_region)

Selected rollout

LIBERO-90 · Task 061 · 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
140
Wall time
8.9s
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 0 140 103 KB
2 Success 1001 2 143 108 KB
3 Success 1002 4 144 105 KB
4 Success 1003 6 134 101 KB
5 Success 1004 8 134 101 KB
6 Success 1005 10 136 98 KB
7 Success 1006 12 139 102 KB
8 Success 1007 14 143 105 KB
9 Success 1008 16 137 105 KB
10 Success 1009 18 145 108 KB
11 Success 1010 20 134 99 KB
12 Success 1011 22 144 104 KB
13 Success 1012 24 143 109 KB
14 Success 1013 26 135 100 KB
15 Success 1014 28 136 100 KB
16 Success 1015 30 137 99 KB
17 Success 1016 32 137 100 KB
18 Success 1017 34 145 107 KB
19 Success 1018 36 135 100 KB
20 Success 1019 38 141 103 KB
21 Success 1020 40 139 101 KB
22 Success 1021 42 142 106 KB
23 Success 1022 44 136 99 KB
24 Success 1023 46 144 105 KB
25 Success 1024 48 144 104 KB
26 Success 1025 0 136 100 KB
27 Success 1026 2 141 105 KB
28 Success 1027 4 142 104 KB
29 Success 1028 6 134 97 KB
30 Success 1029 8 138 105 KB
31 Success 1030 10 140 99 KB
32 Success 1031 12 138 102 KB
33 Success 1032 14 143 105 KB
34 Success 1033 16 138 104 KB
35 Success 1034 18 143 106 KB
36 Success 1035 20 136 100 KB
37 Success 1036 22 151 107 KB
38 Success 1037 24 143 109 KB
39 Success 1038 26 135 100 KB
40 Success 1039 28 135 100 KB
41 Success 1040 30 142 103 KB
42 Success 1041 32 139 101 KB
43 Success 1042 34 143 106 KB
44 Success 1043 36 135 99 KB
45 Success 1044 38 141 104 KB
46 Success 1045 40 143 101 KB
47 Success 1046 42 140 105 KB
48 Success 1047 44 135 98 KB
49 Success 1048 46 150 109 KB
50 Success 1049 48 143 104 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 3:39 PM UTC
Manifest SHA-256
bc54409de3…4960437f
Aggregate SHA-256
a9e7dad9f5…653f0a00
Episode index SHA-256
35815f9acc…cc4ed61d
Validation SHA-256
0be2d3ce11…3b8ba915
Artifact inventory SHA-256
d6a847cb23…4562619f