MolmoAct 2 Evaluation gallery
IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Supplemental Task 004 Validated task

put the butter at the front in the top drawer of the cabinet and close it

Completed task success rate
0.0%
0 of 50
Control horizon
400
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
12m 2s
Task process wall time

Canonical catalog

Task definition

Model instruction
put the butter at the front in the top drawer of the cabinet and close it
BDDL language
put the butter at the front in the top drawer of the cabinet and close it
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. butter 1 is in wooden cabinet 1 top region

    (in butter_1 wooden_cabinet_1_top_region)

  2. wooden cabinet 1 top region is closed

    (close wooden_cabinet_1_top_region)
Exact parsed BDDL goal state 
(in butter_1 wooden_cabinet_1_top_region)
(close wooden_cabinet_1_top_region)

Selected rollout

LIBERO-90 · Task 004 · Episode 1

Failure
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
400
Wall time
16s
Outcome
Failure

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 Failure 1000 0 400 320 KB
2 Failure 1001 1 400 275 KB
3 Failure 1002 2 400 320 KB
4 Failure 1003 3 400 177 KB
5 Failure 1004 4 400 205 KB
6 Failure 1005 5 400 133 KB
7 Failure 1006 6 400 261 KB
8 Failure 1007 7 400 220 KB
9 Failure 1008 8 400 141 KB
10 Failure 1009 9 400 257 KB
11 Failure 1010 10 400 262 KB
12 Failure 1011 11 400 217 KB
13 Failure 1012 12 400 222 KB
14 Failure 1013 13 400 225 KB
15 Failure 1014 14 400 300 KB
16 Failure 1015 15 400 167 KB
17 Failure 1016 16 400 211 KB
18 Failure 1017 17 400 172 KB
19 Failure 1018 18 400 245 KB
20 Failure 1019 19 400 192 KB
21 Failure 1020 20 400 243 KB
22 Failure 1021 21 400 278 KB
23 Failure 1022 22 400 233 KB
24 Failure 1023 23 400 223 KB
25 Failure 1024 24 400 183 KB
26 Failure 1025 25 400 167 KB
27 Failure 1026 26 400 205 KB
28 Failure 1027 27 400 179 KB
29 Failure 1028 28 400 330 KB
30 Failure 1029 29 400 149 KB
31 Failure 1030 30 400 212 KB
32 Failure 1031 31 400 217 KB
33 Failure 1032 32 400 150 KB
34 Failure 1033 33 400 262 KB
35 Failure 1034 34 400 170 KB
36 Failure 1035 35 400 306 KB
37 Failure 1036 36 400 269 KB
38 Failure 1037 37 400 170 KB
39 Failure 1038 38 400 234 KB
40 Failure 1039 39 400 245 KB
41 Failure 1040 40 400 185 KB
42 Failure 1041 41 400 245 KB
43 Failure 1042 42 400 151 KB
44 Failure 1043 43 400 275 KB
45 Failure 1044 44 400 158 KB
46 Failure 1045 45 400 205 KB
47 Failure 1046 46 400 250 KB
48 Failure 1047 47 400 199 KB
49 Failure 1048 48 400 184 KB
50 Failure 1049 49 400 249 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 5:31 AM UTC
Manifest SHA-256
b1b181e017…c06d869d
Aggregate SHA-256
d7ced7ee2b…71ef7544
Episode index SHA-256
82939ec116…533252e8
Validation SHA-256
e7c9a48c68…0eb5fac7
Artifact inventory SHA-256
ccd2727add…0641caf1