MolmoAct 2 Evaluation gallery
IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Supplemental Task 007 Validated task

open the top drawer of the cabinet

Completed task success rate
62.0%
31 of 50
Control horizon
400
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
7m 16s
Task process wall time

Canonical catalog

Task definition

Model instruction
open the top drawer of the cabinet
BDDL language
open the top drawer of the cabinet
Problem
libero_kitchen_tabletop_manipulation
Objects
akita_black_bowl_1, plate_1
Fixtures
kitchen_table, wooden_cabinet_1
Initial-state predicates
3
Fixed init states
50
Exact initial-state predicates 
(on akita_black_bowl_1 kitchen_table_akita_black_bowl_init_region)
(on plate_1 kitchen_table_plate_init_region)
(on wooden_cabinet_1 kitchen_table_wooden_cabinet_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. wooden cabinet 1 top region is open

    (open wooden_cabinet_1_top_region)
Exact parsed BDDL goal state 
(open wooden_cabinet_1_top_region)

Selected rollout

LIBERO-90 · Task 007 · Episode 1

Failure
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
400
Wall time
15s
Outcome
Failure

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 Failure 1000 0 400 308 KB
2 Success 1001 1 83 52 KB
3 Failure 1002 3 400 351 KB
4 Failure 1003 4 400 268 KB
5 Failure 1004 5 400 137 KB
6 Failure 1005 6 400 197 KB
7 Success 1006 7 76 49 KB
8 Success 1007 9 96 57 KB
9 Success 1008 11 91 58 KB
10 Success 1009 13 75 49 KB
11 Success 1010 15 146 78 KB
12 Success 1011 17 80 50 KB
13 Failure 1012 19 400 285 KB
14 Success 1013 20 86 59 KB
15 Success 1014 22 95 58 KB
16 Success 1015 24 98 65 KB
17 Failure 1016 26 400 340 KB
18 Success 1017 27 95 64 KB
19 Success 1018 29 75 53 KB
20 Failure 1019 31 400 278 KB
21 Failure 1020 32 400 247 KB
22 Success 1021 33 94 64 KB
23 Failure 1022 35 400 135 KB
24 Success 1023 36 67 47 KB
25 Success 1024 38 80 51 KB
26 Success 1025 40 90 57 KB
27 Success 1026 42 92 63 KB
28 Failure 1027 44 400 282 KB
29 Success 1028 45 88 55 KB
30 Success 1029 47 86 62 KB
31 Failure 1030 49 400 274 KB
32 Success 1031 0 80 57 KB
33 Failure 1032 2 400 239 KB
34 Failure 1033 3 400 253 KB
35 Success 1034 4 82 60 KB
36 Failure 1035 6 400 229 KB
37 Success 1036 7 79 51 KB
38 Success 1037 9 89 54 KB
39 Success 1038 11 85 55 KB
40 Success 1039 13 73 47 KB
41 Success 1040 15 110 65 KB
42 Success 1041 17 86 53 KB
43 Failure 1042 19 400 272 KB
44 Failure 1043 20 400 274 KB
45 Success 1044 21 94 65 KB
46 Success 1045 23 95 59 KB
47 Success 1046 25 117 68 KB
48 Success 1047 27 94 63 KB
49 Failure 1048 29 400 265 KB
50 Failure 1049 30 400 298 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 6:03 AM UTC
Manifest SHA-256
86e8a25d36…9ce82afc
Aggregate SHA-256
73a271e5ab…c8b446a1
Episode index SHA-256
79df3c300b…35eda0da
Validation SHA-256
b3971fc0fe…3c10444f
Artifact inventory SHA-256
a5dbfda34d…35407dfd