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 000 Validated task

pick up the alphabet soup and place it in the basket

BDDL language: pick the alphabet soup 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
6m 10s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the alphabet soup and place it in the basket
BDDL language
pick the alphabet soup and place it in the basket
Problem
libero_floor_manipulation
Objects
alphabet_soup_1, basket_1, butter_1, cream_cheese_1, milk_1, salad_dressing_1, tomato_sauce_1
Fixtures
floor
Initial-state predicates
7
Fixed init states
50
Exact initial-state predicates 
(on alphabet_soup_1 floor_target_object_region)
(on salad_dressing_1 floor_other_object_region_0)
(on cream_cheese_1 floor_other_object_region_1)
(on milk_1 floor_other_object_region_2)
(on tomato_sauce_1 floor_other_object_region_3)
(on butter_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. alphabet soup 1 is in basket 1 contain region

    (in alphabet_soup_1 basket_1_contain_region)
Exact parsed BDDL goal state 
(in alphabet_soup_1 basket_1_contain_region)

Selected rollout

LIBERO-Object · Task 000 · 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
135
Wall time
8.5s
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 0 135 125 KB
2 Success 1001 2 134 124 KB
3 Success 1002 4 138 125 KB
4 Success 1003 6 142 131 KB
5 Success 1004 8 143 132 KB
6 Success 1005 10 129 115 KB
7 Success 1006 12 132 120 KB
8 Success 1007 14 136 131 KB
9 Success 1008 16 139 127 KB
10 Success 1009 18 129 117 KB
11 Success 1010 20 142 131 KB
12 Success 1011 22 132 116 KB
13 Success 1012 24 140 125 KB
14 Success 1013 26 142 125 KB
15 Success 1014 28 137 125 KB
16 Success 1015 30 137 125 KB
17 Success 1016 32 127 119 KB
18 Success 1017 34 139 124 KB
19 Success 1018 36 137 124 KB
20 Success 1019 38 139 126 KB
21 Success 1020 40 135 123 KB
22 Success 1021 42 137 121 KB
23 Success 1022 44 130 115 KB
24 Success 1023 46 140 130 KB
25 Success 1024 48 138 128 KB
26 Success 1025 0 134 126 KB
27 Success 1026 2 139 128 KB
28 Success 1027 4 137 126 KB
29 Success 1028 6 133 122 KB
30 Success 1029 8 143 133 KB
31 Success 1030 10 130 117 KB
32 Success 1031 12 132 122 KB
33 Success 1032 14 127 119 KB
34 Success 1033 16 127 117 KB
35 Success 1034 18 132 122 KB
36 Success 1035 20 129 121 KB
37 Success 1036 22 151 132 KB
38 Success 1037 24 127 117 KB
39 Success 1038 26 141 126 KB
40 Success 1039 28 138 127 KB
41 Success 1040 30 135 123 KB
42 Success 1041 32 127 120 KB
43 Success 1042 34 139 130 KB
44 Success 1043 36 137 124 KB
45 Success 1044 38 137 124 KB
46 Success 1045 40 128 119 KB
47 Success 1046 42 138 121 KB
48 Success 1047 44 141 128 KB
49 Success 1048 46 129 120 KB
50 Success 1049 48 137 125 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 2:20 AM UTC
Manifest SHA-256
283facf84b…c7a09804
Aggregate SHA-256
c213eab24a…d2463df5
Episode index SHA-256
2a7b5a111d…09fba8b0
Validation SHA-256
dac9907167…0ad90342
Artifact inventory SHA-256
45d3cae0dc…54088fb2