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 009 Validated task

put the yellow and white mug in the microwave and close it

Completed task success rate
88.0%
44 of 50
Control horizon
520
Maximum steps
Camera videos
100
Two per rollout
Evaluation time
9m 34s
Task process wall time

Canonical catalog

Task definition

Model instruction
put the yellow and white mug in the microwave and close it
BDDL language
put the yellow and white mug in the microwave and close it
Problem
libero_kitchen_tabletop_manipulation
Objects
porcelain_mug_1, white_yellow_mug_1
Fixtures
kitchen_table, microwave_1
Initial-state predicates
4
Fixed init states
50
Exact initial-state predicates 
(on porcelain_mug_1 kitchen_table_porcelain_mug_init_region)
(on white_yellow_mug_1 kitchen_table_white_yellow_mug_init_region)
(on microwave_1 kitchen_table_microwave_init_region)
(open microwave_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. white yellow mug 1 is in microwave 1 heating region

    (in white_yellow_mug_1 microwave_1_heating_region)

  2. microwave 1 is closed

    (close microwave_1)
Exact parsed BDDL goal state 
(in white_yellow_mug_1 microwave_1_heating_region)
(close microwave_1)

Selected rollout

LIBERO-10 · Task 009 · 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
248
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 0 248 181 KB
2 Success 1001 2 292 207 KB
3 Success 1002 4 279 213 KB
4 Success 1003 6 227 172 KB
5 Failure 1004 8 520 308 KB
6 Failure 1005 9 520 259 KB
7 Success 1006 10 243 177 KB
8 Success 1007 12 264 206 KB
9 Success 1008 14 243 184 KB
10 Success 1009 16 227 169 KB
11 Success 1010 18 248 191 KB
12 Success 1011 20 254 194 KB
13 Success 1012 22 280 208 KB
14 Success 1013 24 240 179 KB
15 Success 1014 26 248 186 KB
16 Success 1015 28 390 236 KB
17 Success 1016 30 245 182 KB
18 Success 1017 32 230 179 KB
19 Success 1018 34 269 206 KB
20 Success 1019 36 244 182 KB
21 Success 1020 38 245 183 KB
22 Success 1021 40 263 189 KB
23 Success 1022 42 238 178 KB
24 Success 1023 44 259 206 KB
25 Success 1024 46 236 176 KB
26 Success 1025 48 255 194 KB
27 Success 1026 0 246 180 KB
28 Success 1027 2 238 175 KB
29 Failure 1028 4 520 354 KB
30 Failure 1029 5 520 316 KB
31 Success 1030 6 243 174 KB
32 Success 1031 8 252 190 KB
33 Success 1032 10 240 180 KB
34 Success 1033 12 242 179 KB
35 Success 1034 14 234 182 KB
36 Success 1035 16 242 181 KB
37 Success 1036 18 255 194 KB
38 Failure 1037 20 520 344 KB
39 Success 1038 21 230 176 KB
40 Success 1039 23 243 179 KB
41 Success 1040 25 256 183 KB
42 Success 1041 27 251 186 KB
43 Success 1042 29 232 175 KB
44 Success 1043 31 247 189 KB
45 Success 1044 33 244 185 KB
46 Success 1045 35 450 273 KB
47 Failure 1046 37 520 371 KB
48 Success 1047 38 243 179 KB
49 Success 1048 40 251 179 KB
50 Success 1049 42 252 188 KB

Integrity

Task attestation

Status
complete
Completed
Aug 16, 2026, 1:12 AM UTC
Manifest SHA-256
92c0422458…9d987035
Aggregate SHA-256
7aceeade49…cae4b0ff
Episode index SHA-256
133404e0df…d1413c4f
Validation SHA-256
96954be20d…1adb19ca
Artifact inventory SHA-256
9db5df1feb…fe125167