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 005 Validated task

pick up the book and place it in the back compartment of the caddy

Completed task success rate
100.0%
50 of 50
Control horizon
520
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
5m 55s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the book and place it in the back compartment of the caddy
BDDL language
pick up the book and place it in the back compartment of the caddy
Problem
libero_study_tabletop_manipulation
Objects
black_book_1, white_yellow_mug_1
Fixtures
desk_caddy_1, study_table
Initial-state predicates
3
Fixed init states
50
Exact initial-state predicates 
(on desk_caddy_1 study_table_desk_caddy_init_region)
(on black_book_1 study_table_black_book_init_region)
(on white_yellow_mug_1 study_table_white_yellow_mug_init_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. black book 1 is in desk caddy 1 back contain region

    (in black_book_1 desk_caddy_1_back_contain_region)
Exact parsed BDDL goal state 
(in black_book_1 desk_caddy_1_back_contain_region)

Selected rollout

LIBERO-10 · Task 005 · 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
173
Wall time
8.3s
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 0 173 105 KB
2 Success 1001 2 152 98 KB
3 Success 1002 4 191 111 KB
4 Success 1003 6 150 92 KB
5 Success 1004 8 150 92 KB
6 Success 1005 10 161 93 KB
7 Success 1006 12 156 89 KB
8 Success 1007 14 163 100 KB
9 Success 1008 16 148 95 KB
10 Success 1009 18 149 91 KB
11 Success 1010 20 162 89 KB
12 Success 1011 22 140 88 KB
13 Success 1012 24 191 103 KB
14 Success 1013 26 155 93 KB
15 Success 1014 28 154 95 KB
16 Success 1015 30 155 95 KB
17 Success 1016 32 178 105 KB
18 Success 1017 34 167 96 KB
19 Success 1018 36 166 94 KB
20 Success 1019 38 157 94 KB
21 Success 1020 40 166 100 KB
22 Success 1021 42 135 86 KB
23 Success 1022 44 165 98 KB
24 Success 1023 46 151 93 KB
25 Success 1024 48 158 94 KB
26 Success 1025 0 192 109 KB
27 Success 1026 2 155 99 KB
28 Success 1027 4 150 97 KB
29 Success 1028 6 149 92 KB
30 Success 1029 8 165 99 KB
31 Success 1030 10 170 97 KB
32 Success 1031 12 154 89 KB
33 Success 1032 14 188 108 KB
34 Success 1033 16 148 95 KB
35 Success 1034 18 155 92 KB
36 Success 1035 20 161 90 KB
37 Success 1036 22 147 92 KB
38 Success 1037 24 170 98 KB
39 Success 1038 26 163 96 KB
40 Success 1039 28 175 101 KB
41 Success 1040 30 159 95 KB
42 Success 1041 32 163 97 KB
43 Success 1042 34 181 100 KB
44 Success 1043 36 166 96 KB
45 Success 1044 38 168 101 KB
46 Success 1045 40 153 95 KB
47 Success 1046 42 143 89 KB
48 Success 1047 44 171 101 KB
49 Success 1048 46 153 94 KB
50 Success 1049 48 186 108 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 12:29 AM UTC
Manifest SHA-256
8c0394ddf1…8493c211
Aggregate SHA-256
c5ab7d1093…a1c8025c
Episode index SHA-256
c7817d11b8…ede7c37a
Validation SHA-256
ff8801d1bb…0b9723ea
Artifact inventory SHA-256
01c2202193…f4859a8e