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 008 Validated task

put both moka pots on the stove

Completed task success rate
66.0%
33 of 50
Control horizon
520
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
13m 10s
Task process wall time

Canonical catalog

Task definition

Model instruction
put both moka pots on the stove
BDDL language
put both moka pots on the stove
Problem
libero_kitchen_tabletop_manipulation
Objects
moka_pot_1, moka_pot_2
Fixtures
flat_stove_1, kitchen_table
Initial-state predicates
4
Fixed init states
50
Exact initial-state predicates 
(on flat_stove_1 kitchen_table_flat_stove_init_region)
(on moka_pot_1 kitchen_table_moka_pot_right_init_region)
(on moka_pot_2 kitchen_table_moka_pot_left_init_region)
(turnon flat_stove_1)

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. moka pot 1 is on flat stove 1 cook region

    (on moka_pot_1 flat_stove_1_cook_region)

  2. moka pot 2 is on flat stove 1 cook region

    (on moka_pot_2 flat_stove_1_cook_region)

  3. flat stove 1 is turned on

    (turnon flat_stove_1)
Exact parsed BDDL goal state 
(on moka_pot_1 flat_stove_1_cook_region)
(on moka_pot_2 flat_stove_1_cook_region)
(turnon flat_stove_1)

Selected rollout

LIBERO-10 · Task 008 · 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
370
Wall time
15s
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 0 370 253 KB
2 Success 1001 2 500 281 KB
3 Success 1002 4 394 252 KB
4 Failure 1003 6 520 325 KB
5 Success 1004 7 380 248 KB
6 Success 1005 9 476 291 KB
7 Success 1006 11 353 244 KB
8 Failure 1007 13 520 285 KB
9 Failure 1008 14 520 253 KB
10 Success 1009 15 353 236 KB
11 Failure 1010 17 520 354 KB
12 Success 1011 18 416 265 KB
13 Success 1012 20 407 258 KB
14 Success 1013 22 382 253 KB
15 Success 1014 24 377 257 KB
16 Success 1015 26 411 272 KB
17 Success 1016 28 392 247 KB
18 Success 1017 30 369 251 KB
19 Success 1018 32 489 286 KB
20 Success 1019 34 360 240 KB
21 Failure 1020 36 520 279 KB
22 Success 1021 37 405 263 KB
23 Failure 1022 39 520 254 KB
24 Failure 1023 40 520 267 KB
25 Success 1024 41 355 239 KB
26 Success 1025 43 379 256 KB
27 Success 1026 45 346 242 KB
28 Success 1027 47 399 265 KB
29 Failure 1028 49 520 268 KB
30 Success 1029 0 362 253 KB
31 Failure 1030 2 520 279 KB
32 Success 1031 3 376 255 KB
33 Success 1032 5 350 239 KB
34 Success 1033 7 376 247 KB
35 Success 1034 9 378 267 KB
36 Success 1035 11 361 243 KB
37 Failure 1036 13 520 317 KB
38 Failure 1037 14 520 261 KB
39 Failure 1038 15 520 252 KB
40 Success 1039 16 337 231 KB
41 Success 1040 18 424 274 KB
42 Failure 1041 20 520 324 KB
43 Failure 1042 21 520 269 KB
44 Success 1043 22 389 254 KB
45 Failure 1044 24 520 265 KB
46 Success 1045 25 372 252 KB
47 Failure 1046 27 520 253 KB
48 Failure 1047 28 520 279 KB
49 Success 1048 29 399 255 KB
50 Success 1049 31 476 289 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 1:01 AM UTC
Manifest SHA-256
95c0f75b77…cd86b590
Aggregate SHA-256
d5e73e0f11…7292519c
Episode index SHA-256
cf6de089f4…fa3cd868
Validation SHA-256
9a776220e3…9df4132b
Artifact inventory SHA-256
796c19975c…6a6ce38c