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 005 Validated task

pick up the tomato sauce and place it in the basket

BDDL language: pick the tomato sauce 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 49s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the tomato sauce and place it in the basket
BDDL language
pick the tomato sauce and place it in the basket
Problem
libero_floor_manipulation
Objects
basket_1, bbq_sauce_1, butter_1, chocolate_pudding_1, milk_1, orange_juice_1, tomato_sauce_1
Fixtures
floor
Initial-state predicates
7
Fixed init states
50
Exact initial-state predicates 
(on tomato_sauce_1 floor_target_object_region)
(on milk_1 floor_other_object_region_0)
(on butter_1 floor_other_object_region_1)
(on orange_juice_1 floor_other_object_region_2)
(on chocolate_pudding_1 floor_other_object_region_3)
(on bbq_sauce_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. tomato sauce 1 is in basket 1 contain region

    (in tomato_sauce_1 basket_1_contain_region)
Exact parsed BDDL goal state 
(in tomato_sauce_1 basket_1_contain_region)

Selected rollout

LIBERO-Object · Task 005 · 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
119
Wall time
7.6s
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 0 119 122 KB
2 Success 1001 2 154 142 KB
3 Success 1002 4 169 157 KB
4 Success 1003 6 130 130 KB
5 Success 1004 8 128 129 KB
6 Success 1005 10 109 114 KB
7 Success 1006 12 128 132 KB
8 Success 1007 14 118 121 KB
9 Success 1008 16 128 128 KB
10 Success 1009 18 119 119 KB
11 Success 1010 20 130 128 KB
12 Success 1011 22 126 128 KB
13 Success 1012 24 129 126 KB
14 Success 1013 26 129 128 KB
15 Success 1014 28 128 125 KB
16 Success 1015 30 130 127 KB
17 Success 1016 32 120 117 KB
18 Success 1017 34 129 124 KB
19 Success 1018 36 126 127 KB
20 Success 1019 38 132 128 KB
21 Success 1020 40 129 126 KB
22 Success 1021 42 128 130 KB
23 Success 1022 44 132 124 KB
24 Success 1023 46 119 120 KB
25 Success 1024 48 125 124 KB
26 Success 1025 0 126 127 KB
27 Success 1026 2 138 131 KB
28 Success 1027 4 138 129 KB
29 Success 1028 6 122 126 KB
30 Success 1029 8 129 127 KB
31 Success 1030 10 127 126 KB
32 Success 1031 12 127 130 KB
33 Success 1032 14 126 126 KB
34 Success 1033 16 127 127 KB
35 Success 1034 18 127 128 KB
36 Success 1035 20 135 131 KB
37 Success 1036 22 131 128 KB
38 Success 1037 24 129 128 KB
39 Success 1038 26 116 118 KB
40 Success 1039 28 120 120 KB
41 Success 1040 30 129 128 KB
42 Success 1041 32 127 125 KB
43 Success 1042 34 114 117 KB
44 Success 1043 36 128 130 KB
45 Success 1044 38 117 121 KB
46 Success 1045 40 116 119 KB
47 Success 1046 42 127 129 KB
48 Success 1047 44 127 127 KB
49 Success 1048 46 119 119 KB
50 Success 1049 48 129 132 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 2:53 AM UTC
Manifest SHA-256
9f97d2621e…3f85d395
Aggregate SHA-256
d2f7745722…ac092932
Episode index SHA-256
1425eb3e5c…b4ed7e11
Validation SHA-256
93e48e5edd…d653169f
Artifact inventory SHA-256
c7dde9cbce…d053ed0c