BenchmarkPAW-GEN-10-Agentic
Environmente04Connect DC jack
- 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 79:30 Claude Fable 5.2 96:02 Claude Opus 5.5 139:59 DiT-Flow 10:17 GPT-6 Astra 83:52 GR00T N1.7 5:20 MolmoAct 2 8:53 Pi 0.5 12:49 Rho 8:37
- Mean duration
- Gemini 4 Argon 159.0 s Claude Fable 5.2 192.1 s Claude Opus 5.5 280.0 s DiT-Flow 20.6 s GPT-6 Astra 167.7 s GR00T N1.7 10.7 s MolmoAct 2 17.8 s Pi 0.5 25.6 s Rho 17.2 s
- Success
- Gemini 4 Argon 80% Claude Fable 5.2 77% Claude Opus 5.5 57% 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 moving87.3%End-effector moving69.2%Gripper engaged100.0%Contact force > 5 N75.8%Gripper engaged or in contact100.0% Claude Fable 5.2 Share of time manipulating, five definitionsJoints moving61.3%End-effector moving38.8%Gripper engaged86.1%Contact force > 5 N89.8%Gripper engaged or in contact98.6% Claude Opus 5.5 Share of time manipulating, five definitionsJoints moving74.5%End-effector moving45.9%Gripper engaged91.6%Contact force > 5 N53.9%Gripper engaged or in contact95.8% DiT-Flow Share of time manipulating, five definitionsJoints moving93.9%End-effector moving58.1%Gripper engaged7.7%Contact force > 5 N61.9%Gripper engaged or in contact65.6% GPT-6 Astra Share of time manipulating, five definitionsJoints moving72.3%End-effector moving49.0%Gripper engaged84.1%Contact force > 5 N91.5%Gripper engaged or in contact95.8% GR00T N1.7 Share of time manipulating, five definitionsJoints moving99.9%End-effector moving94.6%Gripper engaged25.9%Contact force > 5 N78.9%Gripper engaged or in contact81.7% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving93.7%Gripper engaged91.7%Contact force > 5 N84.3%Gripper engaged or in contact97.7% Pi 0.5 Share of time manipulating, five definitionsJoints moving99.8%End-effector moving94.6%Gripper engaged70.9%Contact force > 5 N64.4%Gripper engaged or in contact92.1% Rho Share of time manipulating, five definitionsJoints moving99.3%End-effector moving93.3%Gripper engaged50.3%Contact force > 5 N72.9%Gripper engaged or in contact84.5%
- 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…
0:002:06