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 008 Validated task

pick up the chocolate pudding and place it in the basket

BDDL language: pick the chocolate pudding 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 13s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the chocolate pudding and place it in the basket
BDDL language
pick the chocolate pudding and place it in the basket
Problem
libero_floor_manipulation
Objects
alphabet_soup_1, basket_1, bbq_sauce_1, chocolate_pudding_1, ketchup_1, orange_juice_1, salad_dressing_1
Fixtures
floor
Initial-state predicates
7
Fixed init states
50
Exact initial-state predicates 
(on chocolate_pudding_1 floor_target_object_region)
(on orange_juice_1 floor_other_object_region_0)
(on bbq_sauce_1 floor_other_object_region_1)
(on ketchup_1 floor_other_object_region_2)
(on salad_dressing_1 floor_other_object_region_3)
(on alphabet_soup_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. chocolate pudding 1 is in basket 1 contain region

    (in chocolate_pudding_1 basket_1_contain_region)
Exact parsed BDDL goal state 
(in chocolate_pudding_1 basket_1_contain_region)

Selected rollout

LIBERO-Object · Task 008 · 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
137
Wall time
8.1s
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 0 137 133 KB
2 Success 1001 2 143 135 KB
3 Success 1002 4 138 132 KB
4 Success 1003 6 138 132 KB
5 Success 1004 8 153 139 KB
6 Success 1005 10 158 140 KB
7 Success 1006 12 144 131 KB
8 Success 1007 14 151 136 KB
9 Success 1008 16 146 137 KB
10 Success 1009 18 143 134 KB
11 Success 1010 20 140 135 KB
12 Success 1011 22 148 134 KB
13 Success 1012 24 138 133 KB
14 Success 1013 26 137 130 KB
15 Success 1014 28 152 139 KB
16 Success 1015 30 148 134 KB
17 Success 1016 32 144 136 KB
18 Success 1017 34 138 128 KB
19 Success 1018 36 144 134 KB
20 Success 1019 38 142 136 KB
21 Success 1020 40 149 139 KB
22 Success 1021 42 150 135 KB
23 Success 1022 44 148 139 KB
24 Success 1023 46 146 134 KB
25 Success 1024 48 141 129 KB
26 Success 1025 0 138 133 KB
27 Success 1026 2 143 134 KB
28 Success 1027 4 137 131 KB
29 Success 1028 6 137 133 KB
30 Success 1029 8 153 139 KB
31 Success 1030 10 157 143 KB
32 Success 1031 12 145 132 KB
33 Success 1032 14 151 134 KB
34 Success 1033 16 152 137 KB
35 Success 1034 18 138 128 KB
36 Success 1035 20 141 136 KB
37 Success 1036 22 148 136 KB
38 Success 1037 24 141 132 KB
39 Success 1038 26 137 130 KB
40 Success 1039 28 152 140 KB
41 Success 1040 30 148 133 KB
42 Success 1041 32 146 135 KB
43 Success 1042 34 143 134 KB
44 Success 1043 36 142 131 KB
45 Success 1044 38 145 135 KB
46 Success 1045 40 150 140 KB
47 Success 1046 42 149 136 KB
48 Success 1047 44 148 140 KB
49 Success 1048 46 144 137 KB
50 Success 1049 48 144 129 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 3:13 AM UTC
Manifest SHA-256
ab45638985…995a3678
Aggregate SHA-256
eca10ad7d5…3cc63839
Episode index SHA-256
578fe8f3e2…954af9c0
Validation SHA-256
aa8121adb6…c7afcb1c
Artifact inventory SHA-256
d352d67b56…7f5a928d