MolmoAct 2 Evaluation gallery
IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Supplemental Task 020 Validated task

turn on the stove

Completed task success rate
100.0%
50 of 50
Control horizon
400
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
4m 17s
Task process wall time

Canonical catalog

Task definition

Model instruction
turn on the stove
BDDL language
turn on the stove
Problem
libero_kitchen_tabletop_manipulation
Objects
chefmate_8_frypan_1, moka_pot_1
Fixtures
flat_stove_1, kitchen_table
Initial-state predicates
3
Fixed init states
50
Exact initial-state predicates 
(on flat_stove_1 kitchen_table_flat_stove_init_region)
(on chefmate_8_frypan_1 kitchen_table_frypan_init_region)
(on moka_pot_1 kitchen_table_moka_pot_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. flat stove 1 is turned on

    (turnon flat_stove_1)
Exact parsed BDDL goal state 
(turnon flat_stove_1)

Selected rollout

LIBERO-90 · Task 020 · 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
86
Wall time
6.3s
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 86 64 KB
2 Success 1001 2 82 63 KB
3 Success 1002 4 74 56 KB
4 Success 1003 6 85 62 KB
5 Success 1004 8 71 55 KB
6 Success 1005 10 88 63 KB
7 Success 1006 12 88 65 KB
8 Success 1007 14 89 64 KB
9 Success 1008 16 77 58 KB
10 Success 1009 18 75 59 KB
11 Success 1010 20 81 65 KB
12 Success 1011 22 84 64 KB
13 Success 1012 24 75 59 KB
14 Success 1013 26 71 56 KB
15 Success 1014 28 85 62 KB
16 Success 1015 30 75 56 KB
17 Success 1016 32 83 65 KB
18 Success 1017 34 77 57 KB
19 Success 1018 36 83 62 KB
20 Success 1019 38 73 55 KB
21 Success 1020 40 75 61 KB
22 Success 1021 42 75 61 KB
23 Success 1022 44 77 63 KB
24 Success 1023 46 83 63 KB
25 Success 1024 48 75 61 KB
26 Success 1025 0 88 63 KB
27 Success 1026 2 75 60 KB
28 Success 1027 4 75 57 KB
29 Success 1028 6 82 61 KB
30 Success 1029 8 73 55 KB
31 Success 1030 10 85 61 KB
32 Success 1031 12 86 63 KB
33 Success 1032 14 91 65 KB
34 Success 1033 16 79 64 KB
35 Success 1034 18 70 56 KB
36 Success 1035 20 83 65 KB
37 Success 1036 22 86 65 KB
38 Success 1037 24 77 59 KB
39 Success 1038 26 73 60 KB
40 Success 1039 28 82 59 KB
41 Success 1040 30 75 60 KB
42 Success 1041 32 77 62 KB
43 Success 1042 34 75 56 KB
44 Success 1043 36 80 61 KB
45 Success 1044 38 71 55 KB
46 Success 1045 40 82 64 KB
47 Success 1046 42 77 59 KB
48 Success 1047 44 80 66 KB
49 Success 1048 46 82 63 KB
50 Success 1049 48 74 61 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 8:32 AM UTC
Manifest SHA-256
7b1a345d4d…7352f24d
Aggregate SHA-256
645a310acf…57eabea9
Episode index SHA-256
2e557b38d2…9d42c9dc
Validation SHA-256
9ab1cb343b…f62bdd44
Artifact inventory SHA-256
812c56c48b…b0cca453