BenchmarkPAW-GEN-10
Environmente10Clamp electrical component
- 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 4:30 Claude Fable 5.2 63:53 Claude Opus 5.5 55:15 DiT-Flow 6:28 Gemini 4 Argon 72:18 GPT-6 Astra 24:13 MolmoAct 2 13:41 Pi 0.5 12:23 Rho 2:05
- Mean duration
- GR00T N1.7 9.0 s Claude Fable 5.2 127.8 s Claude Opus 5.5 110.5 s DiT-Flow 12.9 s Gemini 4 Argon 144.6 s GPT-6 Astra 48.4 s MolmoAct 2 27.4 s Pi 0.5 24.8 s Rho 4.2 s
- Success
- GR00T N1.7 0% Claude Fable 5.2 43% Claude Opus 5.5 20% DiT-Flow 0% Gemini 4 Argon 0% GPT-6 Astra 3% MolmoAct 2 0% Pi 0.5 0% Rho 0%
- Manipulation density
- GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving96.8%Gripper engaged67.5%Contact force > 5 N80.2%Gripper engaged or in contact87.8% Claude Fable 5.2 Share of time manipulating, five definitionsJoints moving79.9%End-effector moving62.6%Gripper engaged93.3%Contact force > 5 N51.4%Gripper engaged or in contact96.8% Claude Opus 5.5 Share of time manipulating, five definitionsJoints moving93.5%End-effector moving84.1%Gripper engaged97.6%Contact force > 5 N83.9%Gripper engaged or in contact97.6% DiT-Flow Share of time manipulating, five definitionsJoints moving96.9%End-effector moving87.2%Gripper engaged47.6%Contact force > 5 N53.5%Gripper engaged or in contact74.4% Gemini 4 Argon Share of time manipulating, five definitionsJoints moving46.6%End-effector moving38.2%Gripper engaged33.1%Contact force > 5 N55.1%Gripper engaged or in contact61.4% GPT-6 Astra Share of time manipulating, five definitionsJoints moving59.1%End-effector moving42.0%Gripper engaged50.4%Contact force > 5 N78.7%Gripper engaged or in contact81.0% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving95.2%Gripper engaged72.7%Contact force > 5 N79.9%Gripper engaged or in contact92.1% Pi 0.5 Share of time manipulating, five definitionsJoints moving98.1%End-effector moving94.3%Gripper engaged86.5%Contact force > 5 N70.0%Gripper engaged or in contact96.3% Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving98.3%Gripper engaged27.5%Contact force > 5 N68.2%Gripper engaged or in contact73.1%
- 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
0:000:08