BenchmarkPAW-GEN-10
Environmente09Open the toolbox with a screwdriver
- Episodes
- MolmoAct 2 30 Claude Fable 5.2 (D10) 30 Claude Opus 5.5 (D10) 30 DiT-Flow 30 Gemini 4 Argon (D10) 30 GPT-6 Astra (D10) 30 GR00T N1.7 30 Pi 0.5 30 Rho 30
- Total duration
- MolmoAct 2 13:46 Claude Fable 5.2 (D10) 125:01 Claude Opus 5.5 (D10) 125:46 DiT-Flow 17:18 Gemini 4 Argon (D10) 69:12 GPT-6 Astra (D10) 58:41 GR00T N1.7 15:08 Pi 0.5 17:37 Rho 16:58
- Mean duration
- MolmoAct 2 27.5 s Claude Fable 5.2 (D10) 250.0 s Claude Opus 5.5 (D10) 251.5 s DiT-Flow 34.6 s Gemini 4 Argon (D10) 138.4 s GPT-6 Astra (D10) 117.4 s GR00T N1.7 30.3 s Pi 0.5 35.2 s Rho 33.9 s
- Success
- MolmoAct 2 33% Claude Fable 5.2 (D10) 70% Claude Opus 5.5 (D10) 17% DiT-Flow 30% Gemini 4 Argon (D10) 0% GPT-6 Astra (D10) 0% GR00T N1.7 20% Pi 0.5 7% Rho 50%
- Manipulation density
- MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving98.0%Gripper engaged65.0%Contact force > 5 N90.1%Gripper engaged or in contact96.3% Claude Fable 5.2 (D10) Share of time manipulating, five definitionsJoints moving90.3%End-effector moving68.3%Gripper engaged73.5%Contact force > 5 N46.5%Gripper engaged or in contact85.4% Claude Opus 5.5 (D10) Share of time manipulating, five definitionsJoints moving88.8%End-effector moving66.4%Gripper engaged66.1%Contact force > 5 N73.5%Gripper engaged or in contact90.8% DiT-Flow Share of time manipulating, five definitionsJoints moving96.8%End-effector moving87.2%Gripper engaged75.6%Contact force > 5 N88.1%Gripper engaged or in contact98.0% Gemini 4 Argon (D10) Share of time manipulating, five definitionsJoints moving50.4%End-effector moving41.7%Gripper engaged8.2%Contact force > 5 N64.6%Gripper engaged or in contact66.1% GPT-6 Astra (D10) Share of time manipulating, five definitionsJoints moving88.7%End-effector moving66.7%Gripper engaged46.2%Contact force > 5 N48.1%Gripper engaged or in contact67.7% GR00T N1.7 Share of time manipulating, five definitionsJoints moving99.4%End-effector moving97.7%Gripper engaged71.9%Contact force > 5 N81.7%Gripper engaged or in contact97.5% Pi 0.5 Share of time manipulating, five definitionsJoints moving99.5%End-effector moving96.2%Gripper engaged77.8%Contact force > 5 N83.8%Gripper engaged or in contact97.7% Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.5%Gripper engaged69.7%Contact force > 5 N88.8%Gripper engaged or in contact95.2%
- SPARC smoothness
- 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. 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. 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. 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. 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…
0:000:15