BenchmarkPAW-GEN-10
Environmente07Place loaded boxes in container (bimanual)
- 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 17:37 Claude Fable 5.2 (D10) 128:05 Claude Opus 5.5 (D10) 42:11 Gemini 4 Argon (D10) 44:18 GPT-6 Astra (D10) 45:32 GR00T N1.7 22:31 MolmoAct 2 20:17 Pi 0.5 19:39 Rho 20:32
- Mean duration
- DiT-Flow 35.2 s Claude Fable 5.2 (D10) 256.2 s Claude Opus 5.5 (D10) 84.4 s Gemini 4 Argon (D10) 88.6 s GPT-6 Astra (D10) 91.1 s GR00T N1.7 45.0 s MolmoAct 2 40.6 s Pi 0.5 39.3 s Rho 41.1 s
- Success
- DiT-Flow 30% Claude Fable 5.2 (D10) 20% Claude Opus 5.5 (D10) 3% Gemini 4 Argon (D10) 3% GPT-6 Astra (D10) 13% GR00T N1.7 27% MolmoAct 2 70% Pi 0.5 13% Rho 67%
- Manipulation density
- DiT-Flow Share of time manipulating, five definitionsJoints moving99.1%End-effector moving88.7%Gripper engaged71.5%Contact force > 5 N69.6%Gripper engaged or in contact90.2% Claude Fable 5.2 (D10) Share of time manipulating, five definitionsJoints moving71.8%End-effector moving38.5%Gripper engaged75.8%Contact force > 5 N78.7%Gripper engaged or in contact91.0% Claude Opus 5.5 (D10) Share of time manipulating, five definitionsJoints moving94.8%End-effector moving73.8%Gripper engaged68.4%Contact force > 5 N81.1%Gripper engaged or in contact82.1% Gemini 4 Argon (D10) Share of time manipulating, five definitionsJoints moving88.7%End-effector moving72.2%Gripper engaged57.3%Contact force > 5 N72.0%Gripper engaged or in contact82.4% GPT-6 Astra (D10) Share of time manipulating, five definitionsJoints moving75.4%End-effector moving50.0%Gripper engaged63.5%Contact force > 5 N73.1%Gripper engaged or in contact78.1% GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.2%Gripper engaged65.2%Contact force > 5 N77.4%Gripper engaged or in contact89.2% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.6%Gripper engaged59.4%Contact force > 5 N77.6%Gripper engaged or in contact84.8% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.7%Gripper engaged67.0%Contact force > 5 N81.5%Gripper engaged or in contact88.2% Rho Share of time manipulating, five definitionsJoints moving99.9%End-effector moving99.7%Gripper engaged65.3%Contact force > 5 N71.1%Gripper engaged or in contact82.0%
- 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
0:000:37