RoboDojo-RC Tier 1 leaderboard
Robocurve’s rerun of six RoboDojo real-world tasks on bimanual YAM arms, with pinned rubrics and a GPT-6 Astra judge that grades each trial from three camera videos. LLM agents get 40 model calls per trial; VLAs run to a 3,600-step cap, and the benchmark README cautions that the two are not directly comparable. Scores are not comparable with RoboDojo-RealEval.
Real robot · I2RT YAM (bimanual)Report an error
65.7%Best · GPT-6.2 Astra
13Models ranked
OpenSaturation
Nov 18, 2026Numbers checked
| # | Model | Type | Score | Date | Source |
|---|---|---|---|---|---|
| 1 | LLM controller | 65.7% | Nov 17, 2026 | ||
| 2 | World-action | 59.3% | Oct 18, 2026 | ||
| 3 | LLM controller | 57.3% | Nov 9, 2026 | ||
| 4 | LLM controller | 54.5% | Nov 5, 2026 | ||
| 5 | LLM controller | 48.2% | Oct 14, 2026 | ||
| 6 | LLM controller | 42.5% | Sep 29, 2026 | ||
| 7 | LLM controller | 41.7% | Oct 2, 2026 | ||
| 8 | LLM controller | 38.2% | Sep 29, 2026 | ||
| 9 | LLM controller | 36.2% | Oct 1, 2026 | ||
| 10 | LLM controller | 22.0% | Sep 29, 2026 | ||
| 11 | VLA | 18.9% | Oct 16, 2026 | ||
| 12 | LLM controller | 14.9% | Sep 29, 2026 | ||
| 13 | VLA | 9.5% | Oct 16, 2026 |
Metric: Mean rubric score (0–1 partial credit per trial) over 6 real tasks, 20 trials each, graded by an LLM judge. One result per model: RoboFYI re-run, then official leaderboard, then paper, then third party. Runs that deviate from the official protocol are listed on the model page but not ranked.
Wrong or missing number? Report an error