MolmoAct 2 Evaluation gallery
IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Supplemental Task 002 Validated task

put the black bowl in the top drawer of the cabinet

Completed task success rate
46.0%
23 of 50
Control horizon
400
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
9m 2s
Task process wall time

Canonical catalog

Task definition

Model instruction
put the black bowl in the top drawer of the cabinet
BDDL language
put the black bowl in the top drawer of the cabinet
Problem
libero_kitchen_tabletop_manipulation
Objects
akita_black_bowl_1, butter_1, butter_2, chocolate_pudding_1
Fixtures
kitchen_table, wooden_cabinet_1
Initial-state predicates
6
Fixed init states
50
Exact initial-state predicates 
(on akita_black_bowl_1 kitchen_table_akita_black_bowl_init_region)
(on butter_1 kitchen_table_butter_front_init_region)
(on butter_2 kitchen_table_butter_back_init_region)
(on chocolate_pudding_1 kitchen_table_chocolate_pudding_init_region)
(on wooden_cabinet_1 kitchen_table_wooden_cabinet_init_region)
(open wooden_cabinet_1_top_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 in wooden cabinet 1 top region

    (in akita_black_bowl_1 wooden_cabinet_1_top_region)
Exact parsed BDDL goal state 
(in akita_black_bowl_1 wooden_cabinet_1_top_region)

Selected rollout

LIBERO-90 · Task 002 · 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
103
Wall time
7.4s
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 0 103 112 KB
2 Success 1001 2 98 109 KB
3 Success 1002 4 140 154 KB
4 Failure 1003 6 400 214 KB
5 Failure 1004 7 400 140 KB
6 Success 1005 8 94 107 KB
7 Success 1006 10 201 151 KB
8 Failure 1007 12 400 186 KB
9 Failure 1008 13 400 243 KB
10 Failure 1009 14 400 233 KB
11 Success 1010 15 84 98 KB
12 Success 1011 17 99 107 KB
13 Failure 1012 19 400 218 KB
14 Failure 1013 20 400 155 KB
15 Success 1014 21 150 157 KB
16 Success 1015 23 95 109 KB
17 Failure 1016 25 400 193 KB
18 Success 1017 26 289 204 KB
19 Failure 1018 28 400 236 KB
20 Failure 1019 29 400 180 KB
21 Success 1020 30 90 99 KB
22 Failure 1021 32 400 205 KB
23 Failure 1022 33 400 212 KB
24 Success 1023 34 92 103 KB
25 Failure 1024 36 400 200 KB
26 Failure 1025 37 400 149 KB
27 Success 1026 38 94 105 KB
28 Success 1027 40 94 104 KB
29 Success 1028 42 103 117 KB
30 Failure 1029 44 400 206 KB
31 Failure 1030 45 400 217 KB
32 Failure 1031 46 400 204 KB
33 Failure 1032 47 400 191 KB
34 Failure 1033 48 400 274 KB
35 Failure 1034 49 400 214 KB
36 Success 1035 0 101 109 KB
37 Success 1036 2 94 109 KB
38 Failure 1037 4 400 214 KB
39 Success 1038 5 101 114 KB
40 Failure 1039 7 400 232 KB
41 Success 1040 8 97 107 KB
42 Failure 1041 10 400 171 KB
43 Failure 1042 11 400 236 KB
44 Failure 1043 12 400 209 KB
45 Success 1044 13 94 105 KB
46 Success 1045 15 94 108 KB
47 Success 1046 17 148 157 KB
48 Failure 1047 19 400 163 KB
49 Failure 1048 20 400 219 KB
50 Success 1049 21 99 110 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 5:05 AM UTC
Manifest SHA-256
26dd14214e…def08cc1
Aggregate SHA-256
870ff9a792…2af8d25f
Episode index SHA-256
ea94e8f11e…14b50be4
Validation SHA-256
afe20c8b4b…04f641cf
Artifact inventory SHA-256
8607106727…caf66e9e