MolmoAct 2 Evaluation gallery
IN PROGRESS · PROVISIONAL Only fully completed, validated task shards are shown. Campaign coverage and aggregate rates can change.
Supplemental Task 035 Validated task

open the microwave

Completed task success rate
52.0%
26 of 50
Control horizon
400
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
8m 51s
Task process wall time

Canonical catalog

Task definition

Model instruction
open the microwave
BDDL language
open the microwave
Problem
libero_kitchen_tabletop_manipulation
Objects
plate_1, white_bowl_1
Fixtures
kitchen_table, microwave_1
Initial-state predicates
4
Fixed init states
50
Exact initial-state predicates 
(on white_bowl_1 microwave_1_top_side)
(on microwave_1 kitchen_table_microwave_init_region)
(close microwave_1)
(on plate_1 kitchen_table_plate_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. microwave 1 is open

    (open microwave_1)
Exact parsed BDDL goal state 
(open microwave_1)

Selected rollout

LIBERO-90 · Task 035 · 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
269
Wall time
11s
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 0 269 191 KB
2 Success 1001 2 277 179 KB
3 Failure 1002 4 400 240 KB
4 Success 1003 5 263 172 KB
5 Failure 1004 7 400 241 KB
6 Failure 1005 8 400 246 KB
7 Failure 1006 9 400 229 KB
8 Success 1007 10 129 100 KB
9 Success 1008 12 157 114 KB
10 Success 1009 14 263 173 KB
11 Failure 1010 16 400 240 KB
12 Success 1011 17 114 92 KB
13 Failure 1012 19 400 250 KB
14 Failure 1013 20 400 109 KB
15 Success 1014 21 153 110 KB
16 Failure 1015 23 400 249 KB
17 Failure 1016 24 400 226 KB
18 Failure 1017 25 400 246 KB
19 Failure 1018 26 400 246 KB
20 Success 1019 27 114 88 KB
21 Success 1020 29 166 121 KB
22 Success 1021 31 259 161 KB
23 Failure 1022 33 400 206 KB
24 Success 1023 34 255 164 KB
25 Failure 1024 36 400 241 KB
26 Success 1025 37 373 208 KB
27 Failure 1026 39 400 253 KB
28 Failure 1027 40 400 244 KB
29 Success 1028 41 116 91 KB
30 Success 1029 43 329 188 KB
31 Success 1030 45 117 94 KB
32 Success 1031 47 285 176 KB
33 Success 1032 49 176 123 KB
34 Failure 1033 1 400 252 KB
35 Success 1034 2 210 146 KB
36 Failure 1035 4 400 232 KB
37 Success 1036 5 269 174 KB
38 Success 1037 7 110 86 KB
39 Failure 1038 9 400 244 KB
40 Failure 1039 10 400 219 KB
41 Success 1040 11 138 106 KB
42 Success 1041 13 113 87 KB
43 Failure 1042 15 400 240 KB
44 Success 1043 16 377 227 KB
45 Failure 1044 18 400 223 KB
46 Failure 1045 19 400 228 KB
47 Failure 1046 20 400 105 KB
48 Failure 1047 21 400 246 KB
49 Success 1048 22 150 113 KB
50 Success 1049 24 391 233 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 11:21 AM UTC
Manifest SHA-256
72df99f429…6abd8d2e
Aggregate SHA-256
e7c8aebf18…0974267e
Episode index SHA-256
7dac1bf559…073e0d80
Validation SHA-256
34315bce80…5ddd8a68
Artifact inventory SHA-256
f3290f421d…baa12db4