MolmoAct 2 Evaluation gallery
IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Supplemental Task 055 Validated task

pick up the alphabet soup 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
5m 35s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the alphabet soup and put it in the tray
BDDL language
pick up the alphabet soup and put it in the tray
Problem
libero_living_room_tabletop_manipulation
Objects
alphabet_soup_1, butter_1, cream_cheese_1, ketchup_1, tomato_sauce_1, wooden_tray_1
Fixtures
living_room_table
Initial-state predicates
6
Fixed init states
50
Exact initial-state predicates 
(on alphabet_soup_1 living_room_table_alphabet_soup_init_region)
(on cream_cheese_1 living_room_table_cream_cheese_init_region)
(on tomato_sauce_1 living_room_table_tomato_sauce_init_region)
(on ketchup_1 living_room_table_ketchup_init_region)
(on butter_1 living_room_table_butter_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. alphabet soup 1 is in wooden tray 1 contain region

    (in alphabet_soup_1 wooden_tray_1_contain_region)
Exact parsed BDDL goal state 
(in alphabet_soup_1 wooden_tray_1_contain_region)

Selected rollout

LIBERO-90 · Task 055 · 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
166
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 0 166 113 KB
2 Success 1001 2 125 89 KB
3 Success 1002 4 118 83 KB
4 Success 1003 6 128 86 KB
5 Success 1004 8 125 86 KB
6 Success 1005 10 112 80 KB
7 Success 1006 12 117 80 KB
8 Success 1007 14 117 82 KB
9 Success 1008 16 117 85 KB
10 Success 1009 18 126 87 KB
11 Success 1010 20 123 85 KB
12 Success 1011 22 130 84 KB
13 Success 1012 24 122 82 KB
14 Success 1013 26 120 82 KB
15 Success 1014 28 135 92 KB
16 Success 1015 30 113 81 KB
17 Success 1016 32 114 81 KB
18 Success 1017 34 113 80 KB
19 Success 1018 36 113 81 KB
20 Success 1019 38 122 84 KB
21 Success 1020 40 119 82 KB
22 Success 1021 42 135 93 KB
23 Success 1022 44 123 86 KB
24 Success 1023 46 119 83 KB
25 Success 1024 48 123 82 KB
26 Success 1025 0 122 85 KB
27 Success 1026 2 125 88 KB
28 Success 1027 4 124 86 KB
29 Success 1028 6 125 87 KB
30 Success 1029 8 141 95 KB
31 Success 1030 10 117 82 KB
32 Success 1031 12 179 116 KB
33 Success 1032 14 115 81 KB
34 Success 1033 16 113 83 KB
35 Success 1034 18 132 89 KB
36 Success 1035 20 129 88 KB
37 Success 1036 22 123 81 KB
38 Success 1037 24 119 80 KB
39 Success 1038 26 133 91 KB
40 Success 1039 28 129 88 KB
41 Success 1040 30 124 86 KB
42 Success 1041 32 118 84 KB
43 Success 1042 34 114 80 KB
44 Success 1043 36 118 83 KB
45 Success 1044 38 121 82 KB
46 Success 1045 40 124 86 KB
47 Success 1046 42 124 86 KB
48 Success 1047 44 121 86 KB
49 Success 1048 46 127 88 KB
50 Success 1049 48 124 84 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 2:42 PM UTC
Manifest SHA-256
d8e84bdc05…ce4512ae
Aggregate SHA-256
de8ba324eb…3508d604
Episode index SHA-256
5b8c8247b4…cbfba3b8
Validation SHA-256
4ee59158d5…dcfbf47a
Artifact inventory SHA-256
29bf09a6f8…1a0d5762