Frontier Vision-Language Models (VLMs) such as GPT-6 Astra have demonstrated remarkable capabilities in robot control, suggesting that broad pretraining provides knowledge valuable for physical action. Yet most Vision-Language-Action (VLA) policies still rely on much smaller VLM backbones, leaving this potential largely untapped. We ask whether frontier-scale representations can provide a stronger foundation for robot learning. We introduce ScaleVLA, which connects a 552B DeepSeek-V4.1-Flash backbone to a trainable action DiT, and systematically compare VLMs from 2B to 552B under a shared training setup. We evaluate three fundamental capabilities of robot foundation models. In sample efficiency, just 10 demonstrations outperform a 2B backbone trained with 50 (87.8% vs. 85.6%). In generalization, LIBERO-PRO success reaches 45.1%, compared with at most 31.3% for smaller backbones. In precise manipulation, real-world charger insertion improves from 4/10 to 9/10 successes, with gains concentrated in contact-sensitive alignment. Despite its scale, ScaleVLA achieves 216 ms median latency per action chunk. Our findings suggest that frontier VLMs can serve not only as reasoning agents, but also as powerful representational foundations for efficient and generalizable robot policies.
Figures & tables
Figure 1: ScaleVLA overview. Top left: backbone sizes. Top right: the VLM encodes images and the instruction, and the action DiT uses these features and robot state to generate an action chunk. Middle: task success by backbone size. Base is the best dense backbone at or below each size. Bottom: inference latency on RoboCasa, sample efficiency on LIBERO Goal, and success on LIBERO and LIBERO-PRO.
Figure 2: ScaleVLA architecture. The VLM encodes the images and the instruction, and the action head reads the output of its causal encoder. The action DiT alternates cross-attention and self-attention and generates an action chunk in four flow steps.
Figure 3: Simulation tasks. LIBERO tests tabletop manipulation, LIBERO-PRO perturbs the objects and scenes of LIBERO, RoboCasa tests kitchen tasks in out-of-distribution scenes, and DexJoCo tests five tasks that require coordinating two dexterous hands.
Backbone
Size label
Architecture
Qwen3-VL-2B
2B
Dense
Cosmos-Reason2-2B
2B
Dense
Cosmos-Reason2-8B
8B
Dense
Qwen3-VL-32B
32B
Dense
Cosmos-Reason2-32B
32B
Dense
DeepSeek-V4.1-Flash-1017
552B
MoE
Table 1: VLM backbones used in the experiments. Sizes refer to the total parameter count of each source model. MoE denotes a mixture of experts.
Figure 4: Backbone size and inference latency. Left: total parameters in each source model. Right: median time per action chunk on RoboCasa, with backbone and action head times shown separately. ScaleVLA uses four H200 GPUs; the other backbones use one each.
Model
Spatial
Object
Goal
Long
Average
π0 [ 5 ]
96.8
98.8
95.8
85.2
94.2
OpenVLA [ 36 ]
84.7
88.4
79.2
53.7
76.5
CoT-VLA [ 93 ]
87.5
91.6
87.6
69.0
83.9
Qwen3-VL-2B
98.4
98.2
90.4
77.8
91.2
Cosmos-Reason2-2B
98.8
97.6
83.2
83.2
90.7
Cosmos-Reason2-8B
99.8
99.0
88.6
87.2
93.7
Table 2: LIBERO success rates (%). The first three rows report published results. Our policies train on each suite’s full demonstration set. The last column averages the four suites. Bold marks the highest success rate in each column.
Goal
Object
Backbone
Env.
Obj.
Env.
Mean
Qwen3-VL-2B
24.2
38.4
25.2
29.3
Cosmos-Reason2-2B
20.6
37.6
11.8
23.3
Cosmos-Reason2-8B
32.6
37.6
23.6
31.3
Qwen3-VL-32B
11.6
44.2
12.6
22.8
Cosmos-Reason2-32B
19.2
38.8
32.4
30.1
Table 3: LIBERO-PRO success rates (%). We test our LIBERO policies from table 2 under environment (Env.) and object (Obj.) perturbations without retraining [ 100 ] .
Backbone
Gen-30
Gen-100
Qwen3-VL-2B
22.4
45.2
Cosmos-Reason2-2B
23.2
42.8
Cosmos-Reason2-8B
25.6
45.6
Qwen3-VL-32B
25.5
43.3
ScaleVLA (552B)
30.7
54.9
Table 4: RoboCasa success rates (%). Gen-30 and Gen-100 use 30 and 100 generated demonstrations per task, respectively. We test in out-of-distribution kitchens.
DP-T [ 13 ]
π0.5 [ 64 ]
Qwen3-VL-2B
Cosmos-Reason2-2B
Cosmos-Reason2-8B
Qwen3-VL-32B
ScaleVLA (552B)
Task
Obj.
Obj.
Obj.
Full
Obj.
Full
Obj.
Full
Obj.
Full
Obj.
Full
Unlock iPad
0.0
0.0
17.3
8.7
15.3
4.7
26.7
6.0
26.7
14.0
31.3
15.3
Hanoi
8.0
4.7
11.3
8.7
24.0
4.7
24.0
13.3
24.0
10.7
28.0
14.0
Assembly
1.3
4.0
4.7
0.0
10.0
0.7
10.7
0.0
4.0
0.0
11.3
1.3
Microwave
42.7
34.7
84.7
61.3
81.3
62.7
82.0
62.0
89.3
62.7
73.3
67.3
Photograph
28.0
7.3
41.3
32.0
54.7
30.7
47.3
24.0
46.7
22.7
66.7
24.0
Table 5: DexJoCo success rates (%). We train one policy on all five bimanual tasks for each backbone and randomization setting (object or full). Bold marks the best of our backbones.
Median latency (ms)
Backbone
GPUs
Tokens
Backbone
Action head
Total
Qwen3-VL-2B
1
212
44.0
69.8
117.2
Cosmos-Reason2-2B
1
212
44.7
67.1
114.7
Cosmos-Reason2-8B
1
212
52.3
69.3
124.8
Qwen3-VL-32B
1
212
69.7
70.5
143.3
Cosmos-Reason2-32B
1
212
68.4
69.0
140.7
Table 6: RoboCasa inference latency. Times are medians per action chunk on H200 GPUs. Bold marks the lowest latency in each timing column.
Goal
Long
N
2B
8B
32B
552B
2B
8B
32B
552B
5
39.4
60.6
61.2
77.4
24.0
40.0
37.6
62.2
10
55.0
70.0
83.0
87.8
56.0
65.2
66.4
75.0
25
85.2
83.0
90.4
97.6
69.6
65.6
83.6
84.6
50
85.6
88.6
95.2
95.4
82.4
87.2
83.8
86.8
Table 7: LIBERO success rates (%) by demonstration count. On Goal and Long, we vary the number of demonstrations per task ( N ) and keep the training budget fixed. The 2B, 8B, and 32B backbones are Cosmos-Reason2 models. Bold marks the best backbone at each demonstration count within each suite.
Figure 5: Plug In Charger on a real robot. Left: all three policies grasp and hand over the charger from in-domain layouts. ScaleVLA aligns and inserts the plug; the other two policies reach the socket but fail to insert the plug. Right: success rates in the in-domain and OOD settings.
Successes
In-domain, median (s)
Latency
Policy
In-domain
OOD
Insertion
Completion
(ms)
Cosmos-Reason2-2B + Action Head
4/10
5/15
85.9
147.1
311
π0.5 + Action Head
8/10
7/15
81.2
132.0
262
ScaleVLA (552B)
9/10
8/15
58.1
114.4
384
Table 8: Real-robot success rates and timing. Successes are counted over ten in-domain and fifteen out-of-distribution (OOD) trials. Insertion and completion times are medians over successful in-domain trials. Latency is the median round trip per action chunk at the robot client. Bold marks the most successes or the shortest time.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Suite
Backbone
2k
5k
10k
20k
40k
Goal
2B
33.4
39.4
51.4
67.4
69.6
552B
77.8
77.4
76.4
77.2
–
Long
2B
10.4
24.0
39.0
50.6
55.2
552B
46.4
62.2
67.0
71.8
–
Appendix
Table 9: LIBERO success rates (%) by training budget. Cosmos-Reason2-2B and ScaleVLA each train with five demonstrations per task. Bold marks the higher success rate when both backbones have results. A dash indicates an unreported result.