BenchmarkPAW-GEN-10
Environmente08Place spray bottles upright, nozzle forward (bimanual handover)
- 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 31:58 Claude Fable 5.2 (D10) 44:59 Claude Opus 5.5 (D10) 61:31 Gemini 4 Argon (D10) 54:01 GPT-6 Astra (D10) 103:04 GR00T N1.7 29:55 MolmoAct 2 29:40 Pi 0.5 31:48 Rho 29:50
- Mean duration
- DiT-Flow 63.9 s Claude Fable 5.2 (D10) 90.0 s Claude Opus 5.5 (D10) 123.0 s Gemini 4 Argon (D10) 108.0 s GPT-6 Astra (D10) 206.1 s GR00T N1.7 59.8 s MolmoAct 2 59.3 s Pi 0.5 63.6 s Rho 59.7 s
- Success
- DiT-Flow 90% Claude Fable 5.2 (D10) 100% Claude Opus 5.5 (D10) 90% Gemini 4 Argon (D10) 90% GPT-6 Astra (D10) 97% GR00T N1.7 73% MolmoAct 2 90% Pi 0.5 83% Rho 87%
- Manipulation density
- DiT-Flow Share of time manipulating, five definitionsJoints moving99.8%End-effector moving98.7%Gripper engaged70.4%Contact force > 5 N73.1%Gripper engaged or in contact92.4% Claude Fable 5.2 (D10) Share of time manipulating, five definitionsJoints moving95.2%End-effector moving79.9%Gripper engaged88.4%Contact force > 5 N65.7%Gripper engaged or in contact94.8% Claude Opus 5.5 (D10) Share of time manipulating, five definitionsJoints moving89.1%End-effector moving78.6%Gripper engaged83.8%Contact force > 5 N81.2%Gripper engaged or in contact91.3% Gemini 4 Argon (D10) Share of time manipulating, five definitionsJoints moving86.8%End-effector moving68.8%Gripper engaged97.5%Contact force > 5 N40.3%Gripper engaged or in contact97.5% GPT-6 Astra (D10) Share of time manipulating, five definitionsJoints moving81.2%End-effector moving53.8%Gripper engaged68.3%Contact force > 5 N46.7%Gripper engaged or in contact80.7% GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.7%Gripper engaged72.0%Contact force > 5 N65.5%Gripper engaged or in contact90.7% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.4%Gripper engaged74.0%Contact force > 5 N74.5%Gripper engaged or in contact93.1% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.5%Gripper engaged72.1%Contact force > 5 N73.4%Gripper engaged or in contact92.8% Rho Share of time manipulating, five definitionsJoints moving99.9%End-effector moving99.5%Gripper engaged71.9%Contact force > 5 N67.1%Gripper engaged or in contact90.2%
- 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
0:001:09