BenchmarkPAW-GEN-10
Environmente08Place spray bottles upright, nozzle forward (bimanual handover)
- Episodes
- GR00T N1.7 30 Claude Fable 5.2 30 Claude Opus 5.5 30 DiT-Flow 30 Gemini 4 Argon 30 GPT-6 Astra 30 MolmoAct 2 30 Pi 0.5 30 Rho 30
- Total duration
- GR00T N1.7 22:29 Claude Fable 5.2 42:10 Claude Opus 5.5 51:18 DiT-Flow 17:16 Gemini 4 Argon 40:02 GPT-6 Astra 90:13 MolmoAct 2 7:19 Pi 0.5 26:09 Rho 5:52
- Mean duration
- GR00T N1.7 45.0 s Claude Fable 5.2 84.3 s Claude Opus 5.5 102.6 s DiT-Flow 34.5 s Gemini 4 Argon 80.1 s GPT-6 Astra 180.4 s MolmoAct 2 14.6 s Pi 0.5 52.3 s Rho 11.7 s
- Success
- GR00T N1.7 0% Claude Fable 5.2 87% Claude Opus 5.5 63% DiT-Flow 0% Gemini 4 Argon 60% GPT-6 Astra 70% MolmoAct 2 0% Pi 0.5 0% Rho 0%
- Manipulation density
- GR00T N1.7 Share of time manipulating, five definitionsJoints moving98.1%End-effector moving89.3%Gripper engaged99.8%Contact force > 5 N86.5%Gripper engaged or in contact99.9% Claude Fable 5.2 Share of time manipulating, five definitionsJoints moving95.0%End-effector moving79.6%Gripper engaged87.5%Contact force > 5 N63.6%Gripper engaged or in contact94.9% Claude Opus 5.5 Share of time manipulating, five definitionsJoints moving88.8%End-effector moving78.8%Gripper engaged77.2%Contact force > 5 N81.6%Gripper engaged or in contact90.9% DiT-Flow Share of time manipulating, five definitionsJoints moving91.7%End-effector moving83.6%Gripper engaged99.7%Contact force > 5 N37.7%Gripper engaged or in contact99.7% Gemini 4 Argon Share of time manipulating, five definitionsJoints moving80.7%End-effector moving63.1%Gripper engaged98.0%Contact force > 5 N45.6%Gripper engaged or in contact98.1% GPT-6 Astra Share of time manipulating, five definitionsJoints moving75.7%End-effector moving50.9%Gripper engaged60.7%Contact force > 5 N46.8%Gripper engaged or in contact79.1% MolmoAct 2 Share of time manipulating, five definitionsJoints moving99.9%End-effector moving98.6%Gripper engaged99.3%Contact force > 5 N69.8%Gripper engaged or in contact99.3% Pi 0.5 Share of time manipulating, five definitionsJoints moving97.2%End-effector moving90.4%Gripper engaged99.8%Contact force > 5 N69.7%Gripper engaged or in contact99.8% Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.2%Gripper engaged49.3%Contact force > 5 N65.8%Gripper engaged or in contact79.0%
- SPARC smoothness
- GR00T N1.7 Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. Claude Fable 5.2 Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. Claude Opus 5.5 Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. DiT-Flow Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. Gemini 4 Argon Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. GPT-6 Astra Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. MolmoAct 2 Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. Pi 0.5 Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015. Rho Spectral arc length of the motionHow directly the arm moved, read from the shape of its speed spectrum. Unitless measure ≤ -1; the closer to -1, the smoother.The measure ignores how large a movement is, so a large and a small one compare directly. Shown here as the mean over this environment's measured episodes.Cutoff10 HzAmplitude threshold5%Zero-padding16×Signalend-effector translationBalasubramanian et al., On the analysis of movement smoothness, J Neuroeng Rehabil 2015.
Episode
Held-out benchmark environment
0:000:07