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 004 Validated task

put the bowl on top of the cabinet

BDDL language: put the bowl on the top of the drawer

Completed task success rate
100.0%
50 of 50
Control horizon
300
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
4m 59s
Task process wall time

Canonical catalog

Task definition

Model instruction
put the bowl on top of the cabinet
BDDL language
put the bowl on the top of the drawer
Problem
libero_tabletop_manipulation
Objects
akita_black_bowl_1, cream_cheese_1, plate_1, wine_bottle_1
Fixtures
flat_stove_1, main_table, wine_rack_1, wooden_cabinet_1
Initial-state predicates
7
Fixed init states
50
Exact initial-state predicates 
(on wine_bottle_1 main_table_wine_bottle_region)
(on akita_black_bowl_1 main_table_akita_black_bowl_region)
(on plate_1 main_table_plate_region)
(on cream_cheese_1 main_table_cream_cheese_region)
(on wooden_cabinet_1 main_table_cabinet_region)
(on flat_stove_1 main_table_stove_region)
(on wine_rack_1 main_table_wine_rack_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. akita black bowl 1 is on wooden cabinet 1 top side

    (on akita_black_bowl_1 wooden_cabinet_1_top_side)
Exact parsed BDDL goal state 
(on akita_black_bowl_1 wooden_cabinet_1_top_side)

Selected rollout

LIBERO-Goal · Task 004 · 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
85
Wall time
6.9s
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 85 96 KB
2 Success 1001 2 82 90 KB
3 Success 1002 4 83 93 KB
4 Success 1003 6 86 94 KB
5 Success 1004 8 81 86 KB
6 Success 1005 10 83 91 KB
7 Success 1006 12 85 89 KB
8 Success 1007 14 86 97 KB
9 Success 1008 16 84 99 KB
10 Success 1009 18 89 100 KB
11 Success 1010 20 85 99 KB
12 Success 1011 22 82 87 KB
13 Success 1012 24 77 89 KB
14 Success 1013 26 89 97 KB
15 Success 1014 28 88 92 KB
16 Success 1015 30 84 95 KB
17 Success 1016 32 82 93 KB
18 Success 1017 34 81 92 KB
19 Success 1018 36 84 92 KB
20 Success 1019 38 86 101 KB
21 Success 1020 40 86 96 KB
22 Success 1021 42 85 92 KB
23 Success 1022 44 83 90 KB
24 Success 1023 46 83 95 KB
25 Success 1024 48 81 95 KB
26 Success 1025 0 84 97 KB
27 Success 1026 2 80 89 KB
28 Success 1027 4 85 93 KB
29 Success 1028 6 84 89 KB
30 Success 1029 8 82 91 KB
31 Success 1030 10 85 102 KB
32 Success 1031 12 83 88 KB
33 Success 1032 14 84 97 KB
34 Success 1033 16 84 99 KB
35 Success 1034 18 88 101 KB
36 Success 1035 20 82 96 KB
37 Success 1036 22 83 97 KB
38 Success 1037 24 78 97 KB
39 Success 1038 26 88 91 KB
40 Success 1039 28 88 94 KB
41 Success 1040 30 87 93 KB
42 Success 1041 32 88 94 KB
43 Success 1042 34 81 91 KB
44 Success 1043 36 87 96 KB
45 Success 1044 38 86 99 KB
46 Success 1045 40 89 98 KB
47 Success 1046 42 84 91 KB
48 Success 1047 44 82 96 KB
49 Success 1048 46 79 86 KB
50 Success 1049 48 84 89 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 1:43 AM UTC
Manifest SHA-256
0e2322e34d…d59823b8
Aggregate SHA-256
45f6ace563…2e9074ec
Episode index SHA-256
9e8bfeec2f…c5d449f8
Validation SHA-256
046e6eaa23…0334fa05
Artifact inventory SHA-256
1f65dd5624…bf09ba95