Scores updated · 22 tests both models report · How we compare
Every test, side by side
All 22 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results22 tests
- MindCubeHY-Embodied 0.5 MoT-2B by 30.166.336.2+30.1
- ShareRobot-Traj.HY-Embodied 0.5 MoT-2B by 22.773.350.6+22.7
- DA-2KHY-Embodied 0.5 MoT-2B by 20.192.372.2+20.1
- ShareRobot-Aff.HY-Embodied 0.5 MoT-2B by 17.826.89+17.8
- ViewSpatialHY-Embodied 0.5 MoT-2B by 1753.136.1+17
- 3DSRBenchHY-Embodied 0.5 MoT-2B by 155742+15
- SITE-Bench-ImageHY-Embodied 0.5 MoT-2B by 12.862.749.9+12.8
- VSI-BenchHY-Embodied 0.5 MoT-2B by 1260.548.5+12
- ERQAHY-Embodied 0.5 MoT-2B by 7.754.546.8+7.7
- EmbSpatial-BenchHY-Embodied 0.5 MoT-2B by 6.682.876.2+6.6
- All-Angles-BenchHY-Embodied 0.5 MoT-2B by 6.155.149+6.1
- RoboSpatial-HomeMiMo Embodied 7B by 6.155.761.8+6.1
- Ego-Plan2HY-Embodied 0.5 MoT-2B by 5.645.539.9+5.6
- RoboBench-MCQHY-Embodied 0.5 MoT-2B by 5.649.243.6+5.6
- SIBench-miniHY-Embodied 0.5 MoT-2B by 5.158.253.1+5.1
- SITE-Bench-VideoHY-Embodied 0.5 MoT-2B by 4.663.558.9+4.6
- RoboBench-PlanningMiMo Embodied 7B by 4.554.258.7+4.5
- Where2PlaceHY-Embodied 0.5 MoT-2B by 4.46863.6+4.4
- RefSpatial-BenchMiMo Embodied 7B by 2.245.848+2.2
- SATMiMo Embodied 7B by 276.778.7+2
- MMSI-BenchHY-Embodied 0.5 MoT-2B by 1.333.231.9+1.3
- CV-Benchtie89.288.8tie
Questions people ask
How do you compare the two?
We use the 22 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.