MolmoAct 2 Evaluation gallery
IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Supplemental Task 043 Validated task

put the white bowl on top of the cabinet

Completed task success rate
90.0%
45 of 50
Control horizon
400
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
6m 19s
Task process wall time

Canonical catalog

Task definition

Model instruction
put the white bowl on top of the cabinet
BDDL language
put the white bowl on top of the cabinet
Problem
libero_kitchen_tabletop_manipulation
Objects
chefmate_8_frypan_1, white_bowl_1
Fixtures
flat_stove_1, kitchen_table, wooden_two_layer_shelf_1
Initial-state predicates
4
Fixed init states
50
Exact initial-state predicates 
(on flat_stove_1 kitchen_table_flat_stove_init_region)
(on chefmate_8_frypan_1 kitchen_table_frypan_init_region)
(on white_bowl_1 kitchen_table_white_bowl_init_region)
(on wooden_two_layer_shelf_1 kitchen_table_wooden_two_layer_shelf_init_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. white bowl 1 is on wooden two layer shelf 1 top side

    (on white_bowl_1 wooden_two_layer_shelf_1_top_side)
Exact parsed BDDL goal state 
(on white_bowl_1 wooden_two_layer_shelf_1_top_side)

Selected rollout

LIBERO-90 · Task 043 · 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
101
Wall time
7.0s
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 0 101 79 KB
2 Success 1001 2 104 83 KB
3 Success 1002 4 103 85 KB
4 Success 1003 6 111 90 KB
5 Success 1004 8 104 85 KB
6 Success 1005 10 138 100 KB
7 Success 1006 12 110 78 KB
8 Success 1007 14 104 81 KB
9 Success 1008 16 111 90 KB
10 Success 1009 18 196 152 KB
11 Success 1010 20 214 166 KB
12 Success 1011 22 104 82 KB
13 Success 1012 24 106 88 KB
14 Success 1013 26 151 115 KB
15 Success 1014 28 104 81 KB
16 Success 1015 30 100 81 KB
17 Success 1016 32 111 90 KB
18 Success 1017 34 104 83 KB
19 Success 1018 36 111 92 KB
20 Success 1019 38 164 137 KB
21 Success 1020 40 110 87 KB
22 Success 1021 42 104 71 KB
23 Success 1022 44 382 250 KB
24 Success 1023 46 116 81 KB
25 Success 1024 48 114 82 KB
26 Success 1025 0 104 76 KB
27 Success 1026 2 141 106 KB
28 Failure 1027 4 400 178 KB
29 Success 1028 5 170 137 KB
30 Success 1029 7 113 90 KB
31 Success 1030 9 139 104 KB
32 Success 1031 11 110 86 KB
33 Success 1032 13 105 83 KB
34 Failure 1033 15 400 174 KB
35 Failure 1034 16 400 247 KB
36 Success 1035 17 154 123 KB
37 Success 1036 19 103 78 KB
38 Success 1037 21 106 84 KB
39 Success 1038 23 111 88 KB
40 Failure 1039 25 400 223 KB
41 Success 1040 26 160 122 KB
42 Success 1041 28 105 83 KB
43 Success 1042 30 100 80 KB
44 Success 1043 32 107 90 KB
45 Success 1044 34 106 86 KB
46 Success 1045 36 112 91 KB
47 Success 1046 38 108 90 KB
48 Success 1047 40 112 89 KB
49 Success 1048 42 103 76 KB
50 Failure 1049 44 400 218 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 12:48 PM UTC
Manifest SHA-256
7c3aaddfcc…6fb79a83
Aggregate SHA-256
12494aed77…c5ca2598
Episode index SHA-256
90683d93ef…886cb57f
Validation SHA-256
a5dc062393…eb415a92
Artifact inventory SHA-256
ad0f83f377…6d719014