Benchmark Almanac

RoboChallenge Table30 v2

LoopWAM 56.8% tops its leaderboard π0.5 0.73% leads the models we track
Not in model cards

Policies run 30 new real tabletop tasks on ARX5, UR5, ALOHA and DOS-W1 robots. Each task has a 10-point stage rubric for partial credit.

Replaced Table30 v1, which retired on May 27th, 2026. The maker says v2 upgrades tasks, evaluation and system. Lightwheel and NVIDIA are building an Isaac Lab twin, announced August 19th, 2026.

Made by
Dexmal + Hugging Face
Released
May 2026
Kind
Real robots
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Last model added
April 2025
Scores refreshed
November 12th, 2026
65
Entries on its own leaderboard, 1 model we track

LoopWAM tops the leaderboard with 56.8%

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is π0.5, at 0.73%.

65 entries. Scroll sideways for the rest.

  1. 56.8 LoopWAM
  2. 54.4 VLA-DM0.5
  3. 44.2 ambase
  4. 41.3 my16
  5. 31.5 Baseline Model
  6. 27.9 holobrain
  7. 27.6 JV0
  8. 23.6 mc
  9. 22.7 test_01
  10. 22.4 pi05_loom
  11. 21.9 W0
  12. 20.8 MagicBot
  13. 20.1 r1
  14. 19.2 hcp-e
  15. 18.7 debuggers_vla
  16. 16.4 Astraeus_V1.7
  17. 16.1 metrics
  18. 15.3 EgoVLA
  19. 14.9 USTB-Linketic
  20. 13.9 Astraeus_V1.5
  21. 13.4 DWC-M
  22. 13.0 ARX5-multitask
  23. 12.8 MultiVLA
  24. 12.7 vict
  25. 12.3 RoboRush
  26. 11.6 Astraeus_V1.6
  27. 10.3 VLA-Agent
  28. 10.1 BrainC
  29. 9.58 AVP
  30. 8.83 xyz
  31. 8.68 TengenX0.1
  32. 8.42 Astraeus_V1
  33. 7.95 UR5-multitask
  34. 7.82 ARX5_PI05
  35. 7.25 smartVLA
  36. 6.28 NGRob
  37. 5.92 ALOHA-multitask
  38. 5.53 DOS-W1-multitask
  39. 5.42 KETI_pi0.5
  40. 5.12 TvT
  41. 4.35 PAGER-press-ARX5
  42. 4.22 EchoMind Master
  43. 4.05 happy_farm
  44. 3.88 UR5_PI05
  45. 3.22 RobotPioneer
  46. 2.97 pi-aloha-base
  47. 2.60 moveon
  48. 2.53 wp
  49. 2.33 pi05_base
  50. 1.92 R0
  51. 1.52 Aloha05
  52. 1.42 WAM_v0
  53. 1.15 M36-E0
  54. 0.73 π0.5
  55. 0.70 DOS_W1_PI05
  56. 0.37 EI-WAM-53M
  57. 0.20 Datawhale-VLA
  58. 0.18 testmulti6
  59. 0.17 vertical
  60. 0.17 ALOHA_PI05
  61. 0.0 pb_vla
  62. 0.0 kp-robot
  63. 0.0 DM-OPD
  64. 0.0 MiniCPM-RobotManip
  65. 0.0 objsight
  1. 1 LoopWAM multi-task policy 56.8%
  2. 2 VLA-DM0.5 multi-task policy 54.4%
  3. 3 ambase multi-task policy 44.2%
  4. 4 my16 multi-task policy 41.3%
  5. 5 Baseline Model multi-task policy 31.5%
  6. 6 holobrain multi-task policy 27.9%
  7. 7 JV0 multi-task policy 27.6%
  8. 8 mc multi-task policy 23.6%
  9. 9 test_01 multi-task policy 22.7%
  10. 10 pi05_loom multi-task policy 22.4%
  11. 11 W0 multi-task policy 21.9%
  12. 12 MagicBot multi-task policy 20.8%
  13. 13 r1 multi-task policy 20.1%
  14. 14 hcp-e multi-task policy 19.2%
  15. 15 debuggers_vla multi-task policy 18.7%
  16. 16 Astraeus_V1.7 multi-task policy 16.4%
  17. 17 metrics multi-task policy 16.1%
  18. 18 EgoVLA multi-task policy 15.3%
  19. 19 USTB-Linketic multi-task policy 14.9%
  20. 20 Astraeus_V1.5 multi-task policy 13.9%
  21. 21 DWC-M single-task policies 13.4%
  22. 22 ARX5-multitask multi-task policy 13%
  23. 23 MultiVLA multi-task policy 12.8%
  24. 24 vict multi-task policy 12.7%
  25. 25 RoboRush multi-task policy 12.3%
  26. 26 Astraeus_V1.6 multi-task policy 11.6%
  27. 27 VLA-Agent multi-task policy 10.3%
  28. 28 BrainC multi-task policy 10.1%
  29. 29 AVP multi-task policy 9.58%
  30. 30 xyz multi-task policy 8.83%
  31. 31 TengenX0.1 multi-task policy 8.68%
  32. 32 Astraeus_V1 multi-task policy 8.42%
  33. 33 UR5-multitask multi-task policy 7.95%
  34. 34 ARX5_PI05 multi-task policy 7.82%
  35. 35 smartVLA multi-task policy 7.25%
  36. 36 NGRob multi-task policy 6.28%
  37. 37 ALOHA-multitask multi-task policy 5.92%
  38. 38 DOS-W1-multitask multi-task policy 5.53%
  39. 39 KETI_pi0.5 multi-task policy 5.42%
  40. 40 TvT multi-task policy 5.12%
  41. 41 PAGER-press-ARX5 multi-task policy 4.35%
  42. 42 EchoMind Master multi-task policy 4.22%
  43. 43 happy_farm multi-task policy 4.05%
  44. 44 UR5_PI05 multi-task policy 3.88%
  45. 45 RobotPioneer multi-task policy 3.22%
  46. 46 pi-aloha-base multi-task policy 2.97%
  47. 47 moveon multi-task policy 2.60%
  48. 48 wp multi-task policy 2.53%
  49. 49 pi05_base multi-task policy 2.33%
  50. 50 R0 multi-task policy 1.92%
  51. 51 Aloha05 multi-task policy 1.52%
  52. 52 WAM_v0 multi-task policy 1.42%
  53. 53 M36-E0 multi-task policy 1.15%
  54. 54 π0.5 multi-task policy 0.73%
  55. 55 DOS_W1_PI05 multi-task policy 0.70%
  56. 56 EI-WAM-53M multi-task policy 0.37%
  57. 57 Datawhale-VLA multi-task policy 0.20%
  58. 58 testmulti6 multi-task policy 0.18%
  59. 59 vertical multi-task policy 0.17%
  60. 60 ALOHA_PI05 multi-task policy 0.17%
  61. 61 pb_vla multi-task policy 0%
  62. 62 kp-robot multi-task policy 0%
  63. 63 DM-OPD multi-task policy 0%
  64. 64 MiniCPM-RobotManip multi-task policy 0%
  65. 65 objsight multi-task policy 0%

Source: Official RoboChallenge Table30 v2 leaderboard

#EntryScoreSettingDateSource
1 LoopWAM 56.8% multi-task policy Sep 2026 Official leaderboard
2 VLA-DM0.5 54.4% multi-task policy Sep 2026 Official leaderboard
3 ambase 44.2% multi-task policy Oct 2026 Official leaderboard
4 my16 41.3% multi-task policy May 2026 Official leaderboard
5 Baseline Model 31.5% multi-task policy Apr 2026 Official leaderboard
6 holobrain 27.9% multi-task policy May 2026 Official leaderboard
7 JV0 27.6% multi-task policy May 2026 Official leaderboard
8 mc 23.6% multi-task policy May 2026 Official leaderboard
9 test_01 22.7% multi-task policy May 2026 Official leaderboard
10 pi05_loom 22.4% multi-task policy Oct 2026 Official leaderboard
11 W0 21.9% multi-task policy May 2026 Official leaderboard
12 MagicBot 20.8% multi-task policy May 2026 Official leaderboard
13 r1 20.1% multi-task policy Oct 2026 Official leaderboard
14 hcp-e 19.2% multi-task policy May 2026 Official leaderboard
15 debuggers_vla 18.7% multi-task policy May 2026 Official leaderboard
16 Astraeus_V1.7 16.4% multi-task policy Sep 2026 Official leaderboard
17 metrics 16.1% multi-task policy May 2026 Official leaderboard
18 EgoVLA 15.3% multi-task policy Oct 2026 Official leaderboard
19 USTB-Linketic 14.9% multi-task policy Aug 2026 Official leaderboard
20 Astraeus_V1.5 13.9% multi-task policy Jul 2026 Official leaderboard
21 DWC-M 13.4% single-task policies Nov 2026 Official leaderboard
22 ARX5-multitask 13% multi-task policy Sep 2026 Official leaderboard
23 MultiVLA 12.8% multi-task policy Sep 2026 Official leaderboard
24 vict 12.7% multi-task policy May 2026 Official leaderboard
25 RoboRush 12.3% multi-task policy May 2026 Official leaderboard
26 Astraeus_V1.6 11.6% multi-task policy Jul 2026 Official leaderboard
27 VLA-Agent 10.3% multi-task policy Oct 2026 Official leaderboard
28 BrainC 10.1% multi-task policy Apr 2026 Official leaderboard
29 AVP 9.58% multi-task policy May 2026 Official leaderboard
30 xyz 8.83% multi-task policy May 2026 Official leaderboard
31 TengenX0.1 8.68% multi-task policy Aug 2026 Official leaderboard
32 Astraeus_V1 8.42% multi-task policy Jun 2026 Official leaderboard
33 UR5-multitask 7.95% multi-task policy Sep 2026 Official leaderboard
34 ARX5_PI05 7.82% multi-task policy Nov 2026 Official leaderboard
35 smartVLA 7.25% multi-task policy May 2026 Official leaderboard
36 NGRob 6.28% multi-task policy May 2026 Official leaderboard
37 ALOHA-multitask 5.92% multi-task policy Aug 2026 Official leaderboard
38 DOS-W1-multitask 5.53% multi-task policy Sep 2026 Official leaderboard
39 KETI_pi0.5 5.42% multi-task policy May 2026 Official leaderboard
40 TvT 5.12% multi-task policy Apr 2026 Official leaderboard
41 PAGER-press-ARX5 4.35% multi-task policy Nov 2026 Official leaderboard
42 EchoMind Master 4.22% multi-task policy May 2026 Official leaderboard
43 happy_farm 4.05% multi-task policy May 2026 Official leaderboard
44 UR5_PI05 3.88% multi-task policy Oct 2026 Official leaderboard
45 RobotPioneer 3.22% multi-task policy May 2026 Official leaderboard
46 pi-aloha-base 2.97% multi-task policy May 2026 Official leaderboard
47 moveon 2.60% multi-task policy May 2026 Official leaderboard
48 wp 2.53% multi-task policy May 2026 Official leaderboard
49 pi05_base 2.33% multi-task policy Oct 2026 Official leaderboard
50 R0 1.92% multi-task policy Apr 2026 Official leaderboard
51 Aloha05 1.52% multi-task policy Jul 2026 Official leaderboard
52 WAM_v0 1.42% multi-task policy Jul 2026 Official leaderboard
53 M36-E0 1.15% multi-task policy Jul 2026 Official leaderboard
54 π0.5 0.73% multi-task policy Apr 2025 Official leaderboard
55 DOS_W1_PI05 0.70% multi-task policy Nov 2026 Official leaderboard
56 EI-WAM-53M 0.37% multi-task policy Sep 2026 Official leaderboard
57 Datawhale-VLA 0.20% multi-task policy May 2026 Official leaderboard
58 testmulti6 0.18% multi-task policy Apr 2026 Official leaderboard
59 vertical 0.17% multi-task policy Apr 2026 Official leaderboard
60 ALOHA_PI05 0.17% multi-task policy Nov 2026 Official leaderboard
61 pb_vla 0% multi-task policy Apr 2026 Official leaderboard
62 kp-robot 0% multi-task policy Jul 2026 Official leaderboard
63 DM-OPD 0% multi-task policy Sep 2026 Official leaderboard
64 MiniCPM-RobotManip 0% multi-task policy Sep 2026 Official leaderboard
65 objsight 0% multi-task policy Sep 2026 Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) π0.5 0% 20% 40% 60% 80% 100% 2025 Near the ceiling (85%) π0.5

Source: Official RoboChallenge Table30 v2 leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

Versions

Replaces RoboChallenge

More in Robotics

All 104 in Robotics
  • ERQA In use 400 multiple-choice visual questions from robot and egocentric footage on spatial, trajectory, action and state reasoning. Accuracy. Gemini Robotics ER 2 78.5%
  • RoboDojo In use Generalist manipulation policies run 42 Isaac Sim tasks and 18 remote real-robot tasks. Scored by task score and success rate. GPT-6 Astra 29%
  • RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate. FLUX 3 Action 42.9%
  • Progress classification (Google DeepMind) In use Models assign each frame of a robot video to one of five task-progress bands from 0 to 100 percent. Scored by accuracy. Gemini Robotics ER 2 57.4%
  • Human proximity (Google DeepMind robotics) In use Models judge from robot camera views whether a human is within 1 meter, a spatial awareness check for safe robot behavior. Scored by accuracy. Gemini Robotics ER 2 93%
  • Moment finding (Google DeepMind) In use Models find the moment in a robot video when an event happens. Scored by accuracy and mean absolute time distance in seconds. Gemini Robotics ER 2 91.3%