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 37.966.328.4+37.9
- ShareRobot-Traj.HY-Embodied 0.5 MoT-2B by 31.773.341.6+31.7
- SATHY-Embodied 0.5 MoT-2B by 31.476.745.3+31.4
- Where2PlaceHY-Embodied 0.5 MoT-2B by 236845+23
- DA-2KHY-Embodied 0.5 MoT-2B by 22.892.369.5+22.8
- RoboBench-PlanningHY-Embodied 0.5 MoT-2B by 1854.236.2+18
- 3DSRBenchHY-Embodied 0.5 MoT-2B by 17.15739.9+17.1
- RefSpatial-BenchHY-Embodied 0.5 MoT-2B by 16.945.828.9+16.9
- SIBench-miniHY-Embodied 0.5 MoT-2B by 16.258.242+16.2
- ViewSpatialHY-Embodied 0.5 MoT-2B by 15.953.137.2+15.9
- All-Angles-BenchHY-Embodied 0.5 MoT-2B by 12.855.142.3+12.8
- ERQAHY-Embodied 0.5 MoT-2B by 12.754.541.8+12.7
- VSI-BenchHY-Embodied 0.5 MoT-2B by 12.560.548+12.5
- RoboBench-MCQHY-Embodied 0.5 MoT-2B by 12.349.236.9+12.3
- SITE-Bench-VideoHY-Embodied 0.5 MoT-2B by 11.363.552.2+11.3
- RoboSpatial-HomeHY-Embodied 0.5 MoT-2B by 10.455.745.3+10.4
- SITE-Bench-ImageHY-Embodied 0.5 MoT-2B by 10.462.752.3+10.4
- Ego-Plan2HY-Embodied 0.5 MoT-2B by 1045.535.5+10
- MMSI-BenchHY-Embodied 0.5 MoT-2B by 9.633.223.6+9.6
- CV-BenchHY-Embodied 0.5 MoT-2B by 9.289.280+9.2
- ShareRobot-Aff.HY-Embodied 0.5 MoT-2B by 726.819.8+7
- EmbSpatial-BenchHY-Embodied 0.5 MoT-2B by 6.982.875.9+6.9
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.