BenchmarkPAW-GEN-10
Environmente04Connect DC jack
- 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 24:53 Claude Fable 5.2 (D10) 94:44 Claude Opus 5.5 (D10) 141:13 Gemini 4 Argon (D10) 77:00 GPT-6 Astra (D10) 79:18 GR00T N1.7 25:00 MolmoAct 2 26:35 Pi 0.5 32:17 Rho 35:31
- Mean duration
- DiT-Flow 49.8 s Claude Fable 5.2 (D10) 189.5 s Claude Opus 5.5 (D10) 282.4 s Gemini 4 Argon (D10) 154.0 s GPT-6 Astra (D10) 158.6 s GR00T N1.7 50.0 s MolmoAct 2 53.2 s Pi 0.5 64.6 s Rho 71.0 s
- Success
- DiT-Flow 7% Claude Fable 5.2 (D10) 83% Claude Opus 5.5 (D10) 47% Gemini 4 Argon (D10) 87% GPT-6 Astra (D10) 0% GR00T N1.7 3% MolmoAct 2 30% Pi 0.5 13% Rho 30%
- Manipulation density
- DiT-Flow Share of time manipulating, five definitionsJoints moving97.8%End-effector moving76.3%Gripper engaged80.9%Contact force > 5 N75.9%Gripper engaged or in contact92.9% Claude Fable 5.2 (D10) Share of time manipulating, five definitionsJoints moving67.5%End-effector moving41.6%Gripper engaged84.7%Contact force > 5 N88.5%Gripper engaged or in contact98.0% Claude Opus 5.5 (D10) Share of time manipulating, five definitionsJoints moving75.0%End-effector moving44.4%Gripper engaged91.2%Contact force > 5 N53.2%Gripper engaged or in contact95.3% Gemini 4 Argon (D10) Share of time manipulating, five definitionsJoints moving89.8%End-effector moving71.2%Gripper engaged100.0%Contact force > 5 N76.5%Gripper engaged or in contact100.0% GPT-6 Astra (D10) Share of time manipulating, five definitionsJoints moving69.8%End-effector moving47.4%Gripper engaged82.4%Contact force > 5 N91.9%Gripper engaged or in contact95.3% GR00T N1.7 Share of time manipulating, five definitionsJoints moving96.5%End-effector moving78.3%Gripper engaged82.0%Contact force > 5 N77.7%Gripper engaged or in contact93.4% MolmoAct 2 Share of time manipulating, five definitionsJoints moving99.5%End-effector moving87.4%Gripper engaged77.5%Contact force > 5 N82.0%Gripper engaged or in contact94.9% Pi 0.5 Share of time manipulating, five definitionsJoints moving99.6%End-effector moving85.6%Gripper engaged84.8%Contact force > 5 N82.2%Gripper engaged or in contact95.8% Rho Share of time manipulating, five definitionsJoints moving99.2%End-effector moving90.3%Gripper engaged78.2%Contact force > 5 N71.8%Gripper engaged or in contact88.9%
- 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
Loading the replay…
0:000:58