BenchmarkPAW-GEN-10
Environmente06Put tools in standing toolbox
- Episodes
- GR00T N1.7 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 MolmoAct 2 30 Pi 0.5 30 Rho 30
- Total duration
- GR00T N1.7 12:57 Claude Fable 5.2 (D10) 87:44 Claude Opus 5.5 (D10) 66:09 DiT-Flow 16:00 Gemini 4 Argon (D10) 58:18 GPT-6 Astra (D10) 25:41 MolmoAct 2 14:19 Pi 0.5 20:05 Rho 15:07
- Mean duration
- GR00T N1.7 25.9 s Claude Fable 5.2 (D10) 175.5 s Claude Opus 5.5 (D10) 132.3 s DiT-Flow 32.0 s Gemini 4 Argon (D10) 116.6 s GPT-6 Astra (D10) 51.4 s MolmoAct 2 28.6 s Pi 0.5 40.2 s Rho 30.2 s
- Success
- GR00T N1.7 0% Claude Fable 5.2 (D10) 77% Claude Opus 5.5 (D10) 3% DiT-Flow 3% Gemini 4 Argon (D10) 3% GPT-6 Astra (D10) 0% MolmoAct 2 3% Pi 0.5 3% Rho 3%
- Manipulation density
- GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.0%Gripper engaged35.2%Contact force > 5 N79.4%Gripper engaged or in contact84.9% Claude Fable 5.2 (D10) Share of time manipulating, five definitionsJoints moving78.2%End-effector moving56.7%Gripper engaged96.6%Contact force > 5 N47.7%Gripper engaged or in contact98.1% Claude Opus 5.5 (D10) Share of time manipulating, five definitionsJoints moving81.3%End-effector moving64.2%Gripper engaged63.7%Contact force > 5 N88.7%Gripper engaged or in contact94.9% DiT-Flow Share of time manipulating, five definitionsJoints moving99.8%End-effector moving98.4%Gripper engaged36.4%Contact force > 5 N86.3%Gripper engaged or in contact91.9% Gemini 4 Argon (D10) Share of time manipulating, five definitionsJoints moving43.4%End-effector moving31.7%Gripper engaged67.8%Contact force > 5 N78.9%Gripper engaged or in contact90.7% GPT-6 Astra (D10) Share of time manipulating, five definitionsJoints moving57.8%End-effector moving40.9%Gripper engaged30.7%Contact force > 5 N38.7%Gripper engaged or in contact60.6% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving97.3%Gripper engaged34.3%Contact force > 5 N85.4%Gripper engaged or in contact89.3% Pi 0.5 Share of time manipulating, five definitionsJoints moving99.6%End-effector moving99.2%Gripper engaged34.0%Contact force > 5 N82.1%Gripper engaged or in contact87.6% Rho Share of time manipulating, five definitionsJoints moving98.3%End-effector moving97.2%Gripper engaged44.7%Contact force > 5 N75.9%Gripper engaged or in contact84.0%
- SPARC smoothness
- 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. 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. 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
0:000:18