BenchmarkPAW-GEN-10
Environmente09Open the toolbox with a screwdriver
- 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 15:14 Claude Fable 5.2 (D10) 139:28 Claude Opus 5.5 (D10) 104:32 Gemini 4 Argon (D10) 59:28 GPT-6 Astra (D10) 53:15 GR00T N1.7 18:46 MolmoAct 2 14:19 Pi 0.5 21:06 Rho 18:05
- Mean duration
- DiT-Flow 30.5 s Claude Fable 5.2 (D10) 278.9 s Claude Opus 5.5 (D10) 209.1 s Gemini 4 Argon (D10) 118.9 s GPT-6 Astra (D10) 106.5 s GR00T N1.7 37.5 s MolmoAct 2 28.6 s Pi 0.5 42.2 s Rho 36.2 s
- Success
- DiT-Flow 0% Claude Fable 5.2 (D10) 0% Claude Opus 5.5 (D10) 7% Gemini 4 Argon (D10) 0% GPT-6 Astra (D10) 0% GR00T N1.7 3% MolmoAct 2 17% Pi 0.5 17% Rho 37%
- Manipulation density
- DiT-Flow Share of time manipulating, five definitionsJoints moving98.7%End-effector moving85.2%Gripper engaged34.7%Contact force > 5 N82.5%Gripper engaged or in contact89.2% Claude Fable 5.2 (D10) Share of time manipulating, five definitionsJoints moving86.8%End-effector moving63.5%Gripper engaged74.4%Contact force > 5 N40.9%Gripper engaged or in contact85.4% Claude Opus 5.5 (D10) Share of time manipulating, five definitionsJoints moving85.4%End-effector moving63.9%Gripper engaged58.7%Contact force > 5 N71.5%Gripper engaged or in contact84.9% Gemini 4 Argon (D10) Share of time manipulating, five definitionsJoints moving86.9%End-effector moving74.2%Gripper engaged59.6%Contact force > 5 N68.8%Gripper engaged or in contact86.6% GPT-6 Astra (D10) Share of time manipulating, five definitionsJoints moving83.4%End-effector moving62.7%Gripper engaged52.4%Contact force > 5 N47.1%Gripper engaged or in contact67.6% GR00T N1.7 Share of time manipulating, five definitionsJoints moving99.6%End-effector moving97.8%Gripper engaged61.1%Contact force > 5 N77.9%Gripper engaged or in contact92.5% MolmoAct 2 Share of time manipulating, five definitionsJoints moving99.9%End-effector moving96.6%Gripper engaged65.9%Contact force > 5 N84.8%Gripper engaged or in contact96.0% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.2%Gripper engaged70.4%Contact force > 5 N84.4%Gripper engaged or in contact96.0% Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving98.7%Gripper engaged72.1%Contact force > 5 N84.1%Gripper engaged or in contact95.2%
- 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
Loading the replay…
0:000:46