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 black bowl on the stove and place it on the plate

BDDL language: pick the akita black bowl on the stove and place it on the plate

Completed task success rate
100.0%
50 of 50
Control horizon
280
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
7m 4s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the black bowl on the stove and place it on the plate
BDDL language
pick the akita black bowl on the stove and place it on the plate
Problem
libero_tabletop_manipulation
Objects
akita_black_bowl_1, akita_black_bowl_2, cookies_1, glazed_rim_porcelain_ramekin_1, plate_1
Fixtures
flat_stove_1, main_table, wooden_cabinet_1
Initial-state predicates
7
Fixed init states
50
Exact initial-state predicates 
(on akita_black_bowl_1 flat_stove_1_cook_region)
(on akita_black_bowl_2 wooden_cabinet_1_top_side)
(on plate_1 main_table_plate_region)
(on cookies_1 main_table_box_region)
(on glazed_rim_porcelain_ramekin_1 main_table_ramekin_region)
(on wooden_cabinet_1 main_table_cabinet_region)
(on flat_stove_1 main_table_stove_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 plate 1

    (on akita_black_bowl_1 plate_1)
Exact parsed BDDL goal state 
(on akita_black_bowl_1 plate_1)

Selected rollout

LIBERO-Spatial · 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
104
Wall time
9.0s
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 0 104 92 KB
2 Success 1001 2 120 108 KB
3 Success 1002 4 118 102 KB
4 Success 1003 6 113 99 KB
5 Success 1004 8 112 92 KB
6 Success 1005 10 119 107 KB
7 Success 1006 12 110 104 KB
8 Success 1007 14 112 100 KB
9 Success 1008 16 102 95 KB
10 Success 1009 18 106 102 KB
11 Success 1010 20 109 96 KB
12 Success 1011 22 107 96 KB
13 Success 1012 24 107 95 KB
14 Success 1013 26 108 90 KB
15 Success 1014 28 110 95 KB
16 Success 1015 30 106 102 KB
17 Success 1016 32 107 93 KB
18 Success 1017 34 116 101 KB
19 Success 1018 36 110 98 KB
20 Success 1019 38 115 104 KB
21 Success 1020 40 109 96 KB
22 Success 1021 42 118 100 KB
23 Success 1022 44 115 100 KB
24 Success 1023 46 116 92 KB
25 Success 1024 48 110 98 KB
26 Success 1025 0 104 100 KB
27 Success 1026 2 115 111 KB
28 Success 1027 4 118 101 KB
29 Success 1028 6 113 106 KB
30 Success 1029 8 110 92 KB
31 Success 1030 10 119 102 KB
32 Success 1031 12 107 87 KB
33 Success 1032 14 105 86 KB
34 Success 1033 16 109 105 KB
35 Success 1034 18 106 103 KB
36 Success 1035 20 110 104 KB
37 Success 1036 22 114 103 KB
38 Success 1037 24 109 97 KB
39 Success 1038 26 104 89 KB
40 Success 1039 28 109 96 KB
41 Success 1040 30 102 94 KB
42 Success 1041 32 113 94 KB
43 Success 1042 34 116 98 KB
44 Success 1043 36 111 102 KB
45 Success 1044 38 115 97 KB
46 Success 1045 40 114 93 KB
47 Success 1046 42 112 107 KB
48 Success 1047 44 117 96 KB
49 Success 1048 46 114 94 KB
50 Success 1049 48 109 97 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 4:16 AM UTC
Manifest SHA-256
828cf4c396…8ad257cd
Aggregate SHA-256
c5479ba066…6a0c9fb2
Episode index SHA-256
149dec7200…eb3d70c6
Validation SHA-256
cb1b4b8a98…b1680ff6
Artifact inventory SHA-256
6d465439d3…a1dcc299