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 006 Validated task

put the cream cheese in the bowl

BDDL language: put the cream cheese on the bowl

Completed task success rate
98.0%
49 of 50
Control horizon
300
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
5m 11s
Task process wall time

Canonical catalog

Task definition

Model instruction
put the cream cheese in the bowl
BDDL language
put the cream cheese on the bowl
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. cream cheese 1 is on akita black bowl 1

    (on cream_cheese_1 akita_black_bowl_1)
Exact parsed BDDL goal state 
(on cream_cheese_1 akita_black_bowl_1)

Selected rollout

LIBERO-Goal · Task 006 · 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
90
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 90 72 KB
2 Success 1001 2 94 74 KB
3 Success 1002 4 82 66 KB
4 Success 1003 6 79 67 KB
5 Success 1004 8 88 69 KB
6 Success 1005 10 78 62 KB
7 Success 1006 12 89 70 KB
8 Success 1007 14 87 68 KB
9 Success 1008 16 88 70 KB
10 Success 1009 18 89 69 KB
11 Success 1010 20 75 64 KB
12 Success 1011 22 87 71 KB
13 Success 1012 24 92 75 KB
14 Success 1013 26 86 69 KB
15 Success 1014 28 80 68 KB
16 Failure 1015 30 300 163 KB
17 Success 1016 31 80 64 KB
18 Success 1017 33 91 73 KB
19 Success 1018 35 78 65 KB
20 Success 1019 37 90 70 KB
21 Success 1020 39 88 71 KB
22 Success 1021 41 93 74 KB
23 Success 1022 43 89 71 KB
24 Success 1023 45 83 68 KB
25 Success 1024 47 93 78 KB
26 Success 1025 49 91 74 KB
27 Success 1026 1 86 69 KB
28 Success 1027 3 91 74 KB
29 Success 1028 5 96 75 KB
30 Success 1029 7 97 79 KB
31 Success 1030 9 86 68 KB
32 Success 1031 11 85 67 KB
33 Success 1032 13 76 65 KB
34 Success 1033 15 82 67 KB
35 Success 1034 17 91 72 KB
36 Success 1035 19 83 67 KB
37 Success 1036 21 84 67 KB
38 Success 1037 23 82 66 KB
39 Success 1038 25 75 64 KB
40 Success 1039 27 85 69 KB
41 Success 1040 29 88 68 KB
42 Success 1041 31 83 66 KB
43 Success 1042 33 88 72 KB
44 Success 1043 35 86 71 KB
45 Success 1044 37 91 70 KB
46 Success 1045 39 83 67 KB
47 Success 1046 41 90 71 KB
48 Success 1047 43 80 67 KB
49 Success 1048 45 87 72 KB
50 Success 1049 47 95 78 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 1:56 AM UTC
Manifest SHA-256
bfec4eee88…54c249f7
Aggregate SHA-256
b9a1e9912e…e8ab5821
Episode index SHA-256
588b08a09b…1ca32d9e
Validation SHA-256
9ebd739931…c75d90cc
Artifact inventory SHA-256
8f91bf726d…ae219d0d