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 008 Validated task

put the bowl on the plate

Completed task success rate
98.0%
49 of 50
Control horizon
300
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
4m 45s
Task process wall time

Canonical catalog

Task definition

Model instruction
put the bowl on the plate
BDDL language
put the bowl on the plate
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. 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-Goal · Task 008 · 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
74
Wall time
6.6s
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 74 79 KB
2 Success 1001 2 72 78 KB
3 Success 1002 4 74 81 KB
4 Success 1003 6 72 77 KB
5 Success 1004 8 72 79 KB
6 Success 1005 10 77 81 KB
7 Success 1006 12 74 78 KB
8 Success 1007 14 69 79 KB
9 Success 1008 16 71 84 KB
10 Success 1009 18 78 82 KB
11 Success 1010 20 75 85 KB
12 Success 1011 22 71 80 KB
13 Success 1012 24 67 77 KB
14 Success 1013 26 68 74 KB
15 Success 1014 28 76 83 KB
16 Success 1015 30 79 77 KB
17 Success 1016 32 73 82 KB
18 Success 1017 34 75 84 KB
19 Success 1018 36 73 83 KB
20 Success 1019 38 72 84 KB
21 Failure 1020 40 300 204 KB
22 Success 1021 41 71 77 KB
23 Success 1022 43 71 80 KB
24 Success 1023 45 73 78 KB
25 Success 1024 47 79 87 KB
26 Success 1025 49 71 82 KB
27 Success 1026 1 76 80 KB
28 Success 1027 3 68 75 KB
29 Success 1028 5 75 77 KB
30 Success 1029 7 71 80 KB
31 Success 1030 9 70 73 KB
32 Success 1031 11 70 80 KB
33 Success 1032 13 72 77 KB
34 Success 1033 15 73 79 KB
35 Success 1034 17 77 85 KB
36 Success 1035 19 77 85 KB
37 Success 1036 21 73 76 KB
38 Success 1037 23 77 79 KB
39 Success 1038 25 76 78 KB
40 Success 1039 27 72 78 KB
41 Success 1040 29 82 88 KB
42 Success 1041 31 75 79 KB
43 Success 1042 33 74 80 KB
44 Success 1043 35 70 79 KB
45 Success 1044 37 76 80 KB
46 Success 1045 39 76 81 KB
47 Success 1046 41 72 75 KB
48 Success 1047 43 70 83 KB
49 Success 1048 45 71 76 KB
50 Success 1049 47 75 85 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 2:07 AM UTC
Manifest SHA-256
dd0f0672d1…fcbf40d3
Aggregate SHA-256
f9afc7da4a…b3099bc6
Episode index SHA-256
6df9ee1a25…18c038f4
Validation SHA-256
d5e49cc2cb…9fd3d158
Artifact inventory SHA-256
6a0b0a3151…01b5defe