RoboChallenge
Fine-tuned policies run 10 real rollouts on each of 30 tabletop tasks across four robot types. Scored by success rate and progress.
Table30 v1 retired 2026-05-27 at 64.33% top success. V2 (dataset RoboChallenge/Table30v2) leader 40.67%. Benchmark team runs every rollout, but host Dexmal also submits its own DM0 models.
In the authors’ words
Testing on real machines is indispensable for robotic control algorithms. In the context of learning-based algorithms, especially VLA models, demand for large-scale evaluation, i.e. testing a large number of models on a large number of tasks, is becoming increasingly urgent. However, doing this right is highly non-trivial, especially when scalability and reproducibility is taken into account. In this report, we describe our methodology for constructing RoboChallenge, an online evaluation system to test robotic control algorithms, and our survey of recent state-of-the-art VLA models using our initial benchmark Table30.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Agent task Many steps in a terminal, browser, desktop, app, game or robot.
Era0 tops the leaderboard with 64.3%
Best score per entry from the benchmark's own leaderboard, read on 2 Nov 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 42.7%.
The newest model with a score here came out in Apr 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 64.3 Era0
- 62.0 DM0
- 51.7 GigaBrain-0.1
- 51.0 Spirit-v1.5
- 45.0 Lira_generalist
- 42.7 π0.5
- 39.7 Atlas_generalist
- 37.3 DM0_generalist
- 35.3 wall-oss-v0.1
- 28.3 π0
- 25.7 VLO
- 21.3 X-VLA
- 17.7 pi05_generalist
- 15.0 RDT-1B
- 14.3 GR00T
- 13.3 GR00T-MULTI
- 12.7 ZR-0_generalist
- 11.7 cogact
- 9.00 pi0_generalist
- 9.00 VLA_test_0204
- 5.00 VLA_test_0119
- 5.00
OpenVLA-OFT
- 1 Era0 64.3%
- 2 DM0 62%
- 3 GigaBrain-0.1 51.7%
- 4 Spirit-v1.5 51%
- 5 Lira_generalist 45%
- 6 π0.5 42.7%
- 7 Atlas_generalist 39.7%
- 8 DM0_generalist 37.3%
- 9 wall-oss-v0.1 35.3%
- 10 π0 28.3%
- 11 VLO 25.7%
- 12 X-VLA 21.3%
- 13 pi05_generalist 17.7%
- 14 RDT-1B 15%
- 15 GR00T 14.3%
- 16 GR00T-MULTI 13.3%
- 17 ZR-0_generalist 12.7%
- 18 cogact 11.7%
- 19 pi0_generalist 9.00%
- 20 VLA_test_0204 9.00%
- 21 VLA_test_0119 5.00%
- 22 OpenVLA-OFT 5.00%
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Era0 | 64.3% | Official leaderboard | ||
| 2 | DM0 | 62% | Official leaderboard | ||
| 3 | GigaBrain-0.1 | 51.7% | Official leaderboard | ||
| 4 | Spirit-v1.5 | 51% | Official leaderboard | ||
| 5 | Lira_generalist | 45% | Official leaderboard | ||
| 6 | π0.5 | 42.7% | Apr 2025 | Official leaderboard | |
| 7 | Atlas_generalist | 39.7% | Official leaderboard | ||
| 8 | DM0_generalist | 37.3% | Official leaderboard | ||
| 9 | wall-oss-v0.1 | 35.3% | Official leaderboard | ||
| 10 | π0 | 28.3% | Oct 2024 | Official leaderboard | |
| 11 | VLO | 25.7% | Official leaderboard | ||
| 12 | X-VLA | 21.3% | Official leaderboard | ||
| 13 | pi05_generalist | 17.7% | Official leaderboard | ||
| 14 | RDT-1B | 15% | Official leaderboard | ||
| 15 | GR00T | 14.3% | Official leaderboard | ||
| 16 | GR00T-MULTI | 13.3% | Official leaderboard | ||
| 17 | ZR-0_generalist | 12.7% | Official leaderboard | ||
| 18 | cogact | 11.7% | Official leaderboard | ||
| 19 | pi0_generalist | 9.00% | Official leaderboard | ||
| 20 | VLA_test_0204 | 9.00% | Official leaderboard | ||
| 21 | VLA_test_0119 | 5.00% | Official leaderboard | ||
| 22 | OpenVLA-OFT | 5.00% | Feb 2025 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.
Versions
More 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% - RoboLab In use Zero-shot DROID Franka policies in Isaac Lab on 120 tabletop tasks at three instruction levels, 10 episodes each. Success rate.
GR00T N1.7 8.58% - 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%
- 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%
- LIBERO Fading Simulated Franka tabletop tasks in four 10-task suites. Policies fine-tuned on 50 demos per task. Success rate over ~50 trials.
MolmoAct 2 97.2%