BenchmarkPAW-GEN-10
Environmente10Clamp electrical component
- Episodes
- DiT-Flow 30 Claude Fable 5.2 (D10) 30 Claude Opus 5.5 (D10) 30 Gemini 4 Argon (D10) 30 GPT-6 Astra (D10) 30 GR00T N1.7 30 MolmoAct 2 30 Pi 0.5 30 Rho 30
- Total duration
- DiT-Flow 13:44 Claude Fable 5.2 (D10) 63:53 Claude Opus 5.5 (D10) 55:15 Gemini 4 Argon (D10) 72:18 GPT-6 Astra (D10) 24:13 GR00T N1.7 6:49 MolmoAct 2 10:18 Pi 0.5 5:16 Rho 13:58
- Mean duration
- DiT-Flow 27.5 s Claude Fable 5.2 (D10) 127.8 s Claude Opus 5.5 (D10) 110.5 s Gemini 4 Argon (D10) 144.6 s GPT-6 Astra (D10) 48.4 s GR00T N1.7 13.6 s MolmoAct 2 20.6 s Pi 0.5 10.5 s Rho 27.9 s
- Success
- DiT-Flow 0% Claude Fable 5.2 (D10) 43% Claude Opus 5.5 (D10) 20% Gemini 4 Argon (D10) 0% GPT-6 Astra (D10) 3% GR00T N1.7 0% MolmoAct 2 0% Pi 0.5 0% Rho 0%
- Manipulation density
- DiT-Flow Share of time manipulating, five definitionsJoints moving99.6%End-effector moving96.0%Gripper engaged36.4%Contact force > 5 N68.8%Gripper engaged or in contact75.9% Claude Fable 5.2 (D10) 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 (D10) 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% Gemini 4 Argon (D10) 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 (D10) 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% GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving98.5%Gripper engaged79.0%Contact force > 5 N81.3%Gripper engaged or in contact93.8% MolmoAct 2 Share of time manipulating, five definitionsJoints moving97.7%End-effector moving78.4%Gripper engaged68.9%Contact force > 5 N79.5%Gripper engaged or in contact87.4% Pi 0.5 Share of time manipulating, five definitionsJoints moving99.9%End-effector moving99.2%Gripper engaged73.8%Contact force > 5 N84.3%Gripper engaged or in contact91.6% Rho Share of time manipulating, five definitionsJoints moving98.5%End-effector moving95.8%Gripper engaged89.0%Contact force > 5 N73.8%Gripper engaged or in contact96.2%
- SPARC smoothness
- 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. Claude Fable 5.2 (D10) 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 (D10) 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 (D10) 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 (D10) 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. 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. 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
0:000:23