MolmoAct 2 Evaluation gallery
Supplemental Task 082 Validated task

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

Completed task success rate
62.0%
31 of 50
Control horizon
400
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
8m 24s
Task process wall time

Canonical catalog

Task definition

Model instruction
pick up the book and place it in the left compartment of the caddy
BDDL language
pick up the book and place it in the left compartment of the caddy
Problem
libero_study_tabletop_manipulation
Objects
black_book_1, porcelain_mug_1, red_coffee_mug_1
Fixtures
desk_caddy_1, study_table
Initial-state predicates
4
Fixed init states
50
Exact initial-state predicates 
(on desk_caddy_1 study_table_desk_caddy_init_region)
(on black_book_1 study_table_desk_caddy_front_left_contain_region)
(on porcelain_mug_1 study_table_porcelain_mug_init_region)
(on red_coffee_mug_1 study_table_red_coffee_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 left contain region

    (in black_book_1 desk_caddy_1_left_contain_region)
Exact parsed BDDL goal state 
(in black_book_1 desk_caddy_1_left_contain_region)

Selected rollout

LIBERO-90 · Task 082 · 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
194
Wall time
9.6s
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 0 194 105 KB
2 Failure 1001 2 400 163 KB
3 Success 1002 3 190 110 KB
4 Success 1003 5 112 66 KB
5 Success 1004 7 271 139 KB
6 Failure 1005 9 400 191 KB
7 Success 1006 10 217 108 KB
8 Success 1007 12 171 98 KB
9 Success 1008 14 117 77 KB
10 Failure 1009 16 400 180 KB
11 Success 1010 17 172 106 KB
12 Failure 1011 19 400 179 KB
13 Success 1012 20 183 103 KB
14 Success 1013 22 158 93 KB
15 Success 1014 24 218 112 KB
16 Success 1015 26 109 71 KB
17 Success 1016 28 265 143 KB
18 Success 1017 30 191 100 KB
19 Failure 1018 32 400 191 KB
20 Failure 1019 33 400 177 KB
21 Success 1020 34 250 124 KB
22 Success 1021 36 216 112 KB
23 Failure 1022 38 400 210 KB
24 Failure 1023 39 400 199 KB
25 Failure 1024 40 400 190 KB
26 Success 1025 41 125 80 KB
27 Success 1026 43 111 70 KB
28 Failure 1027 45 400 199 KB
29 Failure 1028 46 400 196 KB
30 Success 1029 47 193 121 KB
31 Success 1030 49 162 89 KB
32 Success 1031 1 234 134 KB
33 Success 1032 3 201 113 KB
34 Success 1033 5 110 64 KB
35 Success 1034 7 218 113 KB
36 Success 1035 9 156 94 KB
37 Failure 1036 11 400 168 KB
38 Success 1037 12 112 71 KB
39 Success 1038 14 186 106 KB
40 Failure 1039 16 400 218 KB
41 Success 1040 17 189 111 KB
42 Failure 1041 19 400 196 KB
43 Success 1042 20 265 132 KB
44 Failure 1043 22 400 206 KB
45 Failure 1044 23 400 175 KB
46 Failure 1045 24 400 187 KB
47 Success 1046 25 105 71 KB
48 Failure 1047 27 400 197 KB
49 Success 1048 28 223 131 KB
50 Failure 1049 30 400 195 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 7:14 PM UTC
Manifest SHA-256
6f408f8096…235123ac
Aggregate SHA-256
96585188b1…c2c76f1b
Episode index SHA-256
07144799f3…64d47eb9
Validation SHA-256
ca99190360…8d299f93
Artifact inventory SHA-256
d9aec368be…c0f4d9a9