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 17:03 Claude Fable 5.2 (D10) 161:41 Claude Opus 5.5 (D10) 129:42 Gemini 4 Argon (D10) 61:43 GPT-6 Astra (D10) 96:37 GR00T N1.7 13:05 MolmoAct 2 12:54 Pi 0.5 13:58 Rho 16:25
- Mean duration
- DiT-Flow 34.1 s Claude Fable 5.2 (D10) 323.4 s Claude Opus 5.5 (D10) 259.4 s Gemini 4 Argon (D10) 123.4 s GPT-6 Astra (D10) 193.2 s GR00T N1.7 26.2 s MolmoAct 2 25.8 s Pi 0.5 27.9 s Rho 32.8 s
- Success
- DiT-Flow 7% Claude Fable 5.2 (D10) 0% Claude Opus 5.5 (D10) 3% Gemini 4 Argon (D10) 0% GPT-6 Astra (D10) 0% GR00T N1.7 17% MolmoAct 2 33% Pi 0.5 7% Rho 43%
- Manipulation density
- DiT-Flow Share of time manipulating, five definitionsJoints moving95.5%End-effector moving79.7%Gripper engaged78.4%Contact force > 5 N88.6%Gripper engaged or in contact98.3% Claude Fable 5.2 (D10) Share of time manipulating, five definitionsJoints moving84.4%End-effector moving62.1%Gripper engaged75.9%Contact force > 5 N42.8%Gripper engaged or in contact86.0% Claude Opus 5.5 (D10) Share of time manipulating, five definitionsJoints moving87.5%End-effector moving65.1%Gripper engaged66.9%Contact force > 5 N71.5%Gripper engaged or in contact90.4% Gemini 4 Argon (D10) Share of time manipulating, five definitionsJoints moving84.4%End-effector moving73.2%Gripper engaged66.8%Contact force > 5 N70.8%Gripper engaged or in contact91.0% GPT-6 Astra (D10) Share of time manipulating, five definitionsJoints moving90.7%End-effector moving64.5%Gripper engaged66.3%Contact force > 5 N49.9%Gripper engaged or in contact79.3% GR00T N1.7 Share of time manipulating, five definitionsJoints moving99.8%End-effector moving98.2%Gripper engaged70.5%Contact force > 5 N86.6%Gripper engaged or in contact97.7% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving97.1%Gripper engaged63.1%Contact force > 5 N89.8%Gripper engaged or in contact95.4% Pi 0.5 Share of time manipulating, five definitionsJoints moving99.8%End-effector moving97.4%Gripper engaged73.9%Contact force > 5 N90.7%Gripper engaged or in contact97.9% Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.4%Gripper engaged71.9%Contact force > 5 N88.6%Gripper engaged or in contact95.3%
- 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…
0:000:43