BenchmarkPAW-GEN-10
Environmente01Sort screws into bins
- 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 34:13 Claude Fable 5.2 (D10) 39:29 Claude Opus 5.5 (D10) 49:00 Gemini 4 Argon (D10) 69:19 GPT-6 Astra (D10) 67:49 GR00T N1.7 30:39 MolmoAct 2 21:03 Pi 0.5 32:04 Rho 25:52
- Mean duration
- DiT-Flow 68.4 s Claude Fable 5.2 (D10) 79.0 s Claude Opus 5.5 (D10) 98.0 s Gemini 4 Argon (D10) 138.6 s GPT-6 Astra (D10) 135.6 s GR00T N1.7 61.3 s MolmoAct 2 42.1 s Pi 0.5 64.1 s Rho 51.7 s
- Success
- DiT-Flow 0% Claude Fable 5.2 (D10) 100% Claude Opus 5.5 (D10) 100% Gemini 4 Argon (D10) 77% GPT-6 Astra (D10) 100% GR00T N1.7 0% MolmoAct 2 0% Pi 0.5 0% Rho 3%
- Manipulation density
- DiT-Flow Share of time manipulating, five definitionsJoints moving98.5%End-effector moving94.7%Gripper engaged56.0%Contact force > 5 N86.4%Gripper engaged or in contact94.0% Claude Fable 5.2 (D10) Share of time manipulating, five definitionsJoints moving83.4%End-effector moving65.2%Gripper engaged33.9%Contact force > 5 N54.8%Gripper engaged or in contact62.7% Claude Opus 5.5 (D10) Share of time manipulating, five definitionsJoints moving89.1%End-effector moving71.1%Gripper engaged64.4%Contact force > 5 N55.9%Gripper engaged or in contact83.3% Gemini 4 Argon (D10) Share of time manipulating, five definitionsJoints moving66.7%End-effector moving50.1%Gripper engaged94.7%Contact force > 5 N78.3%Gripper engaged or in contact98.4% GPT-6 Astra (D10) Share of time manipulating, five definitionsJoints moving92.5%End-effector moving66.8%Gripper engaged32.3%Contact force > 5 N73.5%Gripper engaged or in contact80.7% GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving98.3%Gripper engaged68.4%Contact force > 5 N74.1%Gripper engaged or in contact95.4% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving94.6%Gripper engaged55.9%Contact force > 5 N89.8%Gripper engaged or in contact95.5% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.2%Gripper engaged48.7%Contact force > 5 N89.1%Gripper engaged or in contact93.6% Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving97.0%Gripper engaged53.6%Contact force > 5 N82.9%Gripper engaged or in contact90.7%
- 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…
0:000:28