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 007 Validated task

put both the alphabet soup and the cream cheese box in the basket

Completed task success rate
100.0%
50 of 50
Control horizon
520
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
8m 52s
Task process wall time

Canonical catalog

Task definition

Model instruction
put both the alphabet soup and the cream cheese box in the basket
BDDL language
put both the alphabet soup and the cream cheese box in the basket
Problem
libero_living_room_tabletop_manipulation
Objects
alphabet_soup_1, basket_1, cream_cheese_1, ketchup_1, tomato_sauce_1
Fixtures
living_room_table
Initial-state predicates
5
Fixed init states
50
Exact initial-state predicates 
(on alphabet_soup_1 living_room_table_alphabet_soup_init_region)
(on cream_cheese_1 living_room_table_cream_cheese_init_region)
(on tomato_sauce_1 living_room_table_tomato_sauce_init_region)
(on ketchup_1 living_room_table_ketchup_init_region)
(on basket_1 living_room_table_basket_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. alphabet soup 1 is in basket 1 contain region

    (in alphabet_soup_1 basket_1_contain_region)

  2. cream cheese 1 is in basket 1 contain region

    (in cream_cheese_1 basket_1_contain_region)
Exact parsed BDDL goal state 
(in alphabet_soup_1 basket_1_contain_region)
(in cream_cheese_1 basket_1_contain_region)

Selected rollout

LIBERO-10 · Task 007 · 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
242
Wall time
12s
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 0 242 178 KB
2 Success 1001 2 231 173 KB
3 Success 1002 4 281 202 KB
4 Success 1003 6 250 181 KB
5 Success 1004 8 259 197 KB
6 Success 1005 10 287 194 KB
7 Success 1006 12 250 174 KB
8 Success 1007 14 271 196 KB
9 Success 1008 16 258 191 KB
10 Success 1009 18 257 189 KB
11 Success 1010 20 236 178 KB
12 Success 1011 22 234 177 KB
13 Success 1012 24 244 178 KB
14 Success 1013 26 237 181 KB
15 Success 1014 28 262 199 KB
16 Success 1015 30 248 185 KB
17 Success 1016 32 255 188 KB
18 Success 1017 34 248 183 KB
19 Success 1018 36 254 191 KB
20 Success 1019 38 256 187 KB
21 Success 1020 40 260 191 KB
22 Success 1021 42 232 170 KB
23 Success 1022 44 259 190 KB
24 Success 1023 46 262 187 KB
25 Success 1024 48 247 181 KB
26 Success 1025 0 247 184 KB
27 Success 1026 2 222 172 KB
28 Success 1027 4 282 200 KB
29 Success 1028 6 257 191 KB
30 Success 1029 8 260 194 KB
31 Success 1030 10 288 190 KB
32 Success 1031 12 249 177 KB
33 Success 1032 14 258 192 KB
34 Success 1033 16 261 193 KB
35 Success 1034 18 242 177 KB
36 Success 1035 20 238 171 KB
37 Success 1036 22 243 183 KB
38 Success 1037 24 250 177 KB
39 Success 1038 26 239 181 KB
40 Success 1039 28 260 202 KB
41 Success 1040 30 256 198 KB
42 Success 1041 32 279 198 KB
43 Success 1042 34 253 193 KB
44 Success 1043 36 269 200 KB
45 Success 1044 38 234 173 KB
46 Success 1045 40 268 195 KB
47 Success 1046 42 229 173 KB
48 Success 1047 44 248 178 KB
49 Success 1048 46 268 189 KB
50 Success 1049 48 243 183 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 12:48 AM UTC
Manifest SHA-256
1c61a8746e…2a8f0363
Aggregate SHA-256
a89e215074…fff478c9
Episode index SHA-256
55d8759d21…76b0e43c
Validation SHA-256
cf697096a9…ba8fb550
Artifact inventory SHA-256
a5fa750a4a…749ea95d