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 003 Validated task

pick up the black bowl on the cookie box and place it on the plate

BDDL language: pick the akita black bowl on the cookies box and place it on the plate

Completed task success rate
98.0%
49 of 50
Control horizon
280
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
6m 13s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the black bowl on the cookie box and place it on the plate
BDDL language
pick the akita black bowl on the cookies box and place it on the plate
Problem
libero_tabletop_manipulation
Objects
akita_black_bowl_1, akita_black_bowl_2, cookies_1, glazed_rim_porcelain_ramekin_1, plate_1
Fixtures
flat_stove_1, main_table, wooden_cabinet_1
Initial-state predicates
7
Fixed init states
50
Exact initial-state predicates 
(on akita_black_bowl_1 cookies_1)
(on akita_black_bowl_2 wooden_cabinet_1_top_side)
(on plate_1 main_table_plate_region)
(on cookies_1 main_table_box_region)
(on glazed_rim_porcelain_ramekin_1 main_table_ramekin_region)
(on wooden_cabinet_1 main_table_cabinet_region)
(on flat_stove_1 main_table_stove_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-Spatial · Task 003 · 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
80
Wall time
7.8s
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 80 83 KB
2 Success 1001 2 86 80 KB
3 Success 1002 4 82 78 KB
4 Success 1003 6 85 78 KB
5 Success 1004 8 85 80 KB
6 Success 1005 10 88 81 KB
7 Success 1006 12 81 79 KB
8 Success 1007 14 84 82 KB
9 Success 1008 16 87 79 KB
10 Success 1009 18 81 76 KB
11 Success 1010 20 93 77 KB
12 Success 1011 22 76 82 KB
13 Success 1012 24 85 80 KB
14 Success 1013 26 79 75 KB
15 Success 1014 28 86 79 KB
16 Success 1015 30 87 78 KB
17 Failure 1016 32 280 295 KB
18 Success 1017 33 83 78 KB
19 Success 1018 35 82 77 KB
20 Success 1019 37 86 83 KB
21 Success 1020 39 87 83 KB
22 Success 1021 41 80 84 KB
23 Success 1022 43 77 77 KB
24 Success 1023 45 86 82 KB
25 Success 1024 47 86 89 KB
26 Success 1025 49 85 80 KB
27 Success 1026 1 81 76 KB
28 Success 1027 3 89 84 KB
29 Success 1028 5 87 80 KB
30 Success 1029 7 85 77 KB
31 Success 1030 9 84 83 KB
32 Success 1031 11 77 82 KB
33 Success 1032 13 80 79 KB
34 Success 1033 15 125 129 KB
35 Success 1034 17 83 82 KB
36 Success 1035 19 77 83 KB
37 Success 1036 21 82 82 KB
38 Success 1037 23 126 136 KB
39 Success 1038 25 77 81 KB
40 Success 1039 27 81 79 KB
41 Success 1040 29 87 75 KB
42 Success 1041 31 80 80 KB
43 Success 1042 33 84 80 KB
44 Success 1043 35 82 77 KB
45 Success 1044 37 85 83 KB
46 Success 1045 39 84 87 KB
47 Success 1046 41 75 74 KB
48 Success 1047 43 80 83 KB
49 Success 1048 45 85 83 KB
50 Success 1049 47 79 87 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 3:45 AM UTC
Manifest SHA-256
cce17fb460…2bcaa48d
Aggregate SHA-256
00df7a0e38…02bee8f5
Episode index SHA-256
42ecf8cecf…3b7ad509
Validation SHA-256
f831476848…b515976e
Artifact inventory SHA-256
fe89f96bed…97a2e20c