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 007 Validated task

pick up the milk and place it in the basket

BDDL language: pick the milk and place it in the basket

Completed task success rate
100.0%
50 of 50
Control horizon
280
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
5m 50s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the milk and place it in the basket
BDDL language
pick the milk and place it in the basket
Problem
libero_floor_manipulation
Objects
basket_1, butter_1, chocolate_pudding_1, cream_cheese_1, milk_1, orange_juice_1, tomato_sauce_1
Fixtures
floor
Initial-state predicates
7
Fixed init states
50
Exact initial-state predicates 
(on milk_1 floor_target_object_region)
(on cream_cheese_1 floor_other_object_region_0)
(on tomato_sauce_1 floor_other_object_region_1)
(on butter_1 floor_other_object_region_2)
(on orange_juice_1 floor_other_object_region_3)
(on chocolate_pudding_1 floor_other_object_region_4)
(on basket_1 floor_bin_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. milk 1 is in basket 1 contain region

    (in milk_1 basket_1_contain_region)
Exact parsed BDDL goal state 
(in milk_1 basket_1_contain_region)

Selected rollout

LIBERO-Object · Task 007 · 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
120
Wall time
7.5s
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 0 120 115 KB
2 Success 1001 2 129 121 KB
3 Success 1002 4 131 128 KB
4 Success 1003 6 188 177 KB
5 Success 1004 8 130 126 KB
6 Success 1005 10 130 119 KB
7 Success 1006 12 117 117 KB
8 Success 1007 14 133 138 KB
9 Success 1008 16 138 129 KB
10 Success 1009 18 129 124 KB
11 Success 1010 20 124 120 KB
12 Success 1011 22 197 175 KB
13 Success 1012 24 140 134 KB
14 Success 1013 26 119 117 KB
15 Success 1014 28 122 119 KB
16 Success 1015 30 117 119 KB
17 Success 1016 32 163 154 KB
18 Success 1017 34 128 121 KB
19 Success 1018 36 123 119 KB
20 Success 1019 38 131 127 KB
21 Success 1020 40 126 120 KB
22 Success 1021 42 130 120 KB
23 Success 1022 44 127 120 KB
24 Success 1023 46 131 122 KB
25 Success 1024 48 121 117 KB
26 Success 1025 0 120 116 KB
27 Success 1026 2 131 121 KB
28 Success 1027 4 127 123 KB
29 Success 1028 6 171 158 KB
30 Success 1029 8 138 127 KB
31 Success 1030 10 131 120 KB
32 Success 1031 12 120 119 KB
33 Success 1032 14 139 147 KB
34 Success 1033 16 135 130 KB
35 Success 1034 18 127 122 KB
36 Success 1035 20 121 116 KB
37 Success 1036 22 119 116 KB
38 Success 1037 24 131 123 KB
39 Success 1038 26 121 118 KB
40 Success 1039 28 122 119 KB
41 Success 1040 30 119 118 KB
42 Success 1041 32 125 123 KB
43 Success 1042 34 123 118 KB
44 Success 1043 36 118 118 KB
45 Success 1044 38 136 127 KB
46 Success 1045 40 128 124 KB
47 Success 1046 42 130 121 KB
48 Success 1047 44 128 120 KB
49 Success 1048 46 133 123 KB
50 Success 1049 48 122 120 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 3:06 AM UTC
Manifest SHA-256
43bc247c34…7df641c8
Aggregate SHA-256
aa36b320dc…78072d42
Episode index SHA-256
83007644ea…87d1cce3
Validation SHA-256
bbfd03a1f8…6c09ad73
Artifact inventory SHA-256
0481232289…1ee5bd91