BenchmarkPAW-GEN-10-Agentic
Environmente05Route cable through closed hoops
- Episodes
- Gemini 4 Argon 30 Claude Fable 5.2 30 Claude Opus 5.5 30 DiT-Flow 30 GPT-6 Astra 30 GR00T N1.7 30 MolmoAct 2 30 Pi 0.5 30 Rho 30
- Total duration
- Gemini 4 Argon 72:34 Claude Fable 5.2 88:24 Claude Opus 5.5 94:58 DiT-Flow 9:53 GPT-6 Astra 83:38 GR00T N1.7 9:34 MolmoAct 2 11:20 Pi 0.5 5:00 Rho 23:10
- Mean duration
- Gemini 4 Argon 145.1 s Claude Fable 5.2 176.8 s Claude Opus 5.5 189.9 s DiT-Flow 19.8 s GPT-6 Astra 167.3 s GR00T N1.7 19.1 s MolmoAct 2 22.7 s Pi 0.5 10.0 s Rho 46.3 s
- Success
- Gemini 4 Argon 3% Claude Fable 5.2 47% Claude Opus 5.5 0% DiT-Flow 0% GPT-6 Astra 0% GR00T N1.7 0% MolmoAct 2 0% Pi 0.5 0% Rho 0%
- Manipulation density
- Gemini 4 Argon Share of time manipulating, five definitionsJoints moving60.1%End-effector moving51.1%Gripper engaged23.3%Contact force > 5 N59.0%Gripper engaged or in contact64.6% Claude Fable 5.2 Share of time manipulating, five definitionsJoints moving84.1%End-effector moving67.5%Gripper engaged96.7%Contact force > 5 N53.0%Gripper engaged or in contact98.1% Claude Opus 5.5 Share of time manipulating, five definitionsJoints moving67.4%End-effector moving50.8%Gripper engaged60.4%Contact force > 5 N77.0%Gripper engaged or in contact87.5% DiT-Flow Share of time manipulating, five definitionsJoints moving97.3%End-effector moving88.2%Gripper engaged50.8%Contact force > 5 N86.4%Gripper engaged or in contact91.5% GPT-6 Astra Share of time manipulating, five definitionsJoints moving66.3%End-effector moving47.3%Gripper engaged48.8%Contact force > 5 N47.0%Gripper engaged or in contact71.3% GR00T N1.7 Share of time manipulating, five definitionsJoints moving98.7%End-effector moving89.3%Gripper engaged71.8%Contact force > 5 N91.4%Gripper engaged or in contact94.8% MolmoAct 2 Share of time manipulating, five definitionsJoints moving96.9%End-effector moving84.0%Gripper engaged71.2%Contact force > 5 N82.0%Gripper engaged or in contact93.5% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving98.8%Gripper engaged23.3%Contact force > 5 N89.7%Gripper engaged or in contact90.7% Rho Share of time manipulating, five definitionsJoints moving99.8%End-effector moving96.7%Gripper engaged99.8%Contact force > 5 N82.0%Gripper engaged or in contact99.8%
- SPARC smoothness
- Gemini 4 Argon 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 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 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. GPT-6 Astra 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…
0:001:33