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 74:56 Claude Fable 5.2 82:29 Claude Opus 5.5 105:48 DiT-Flow 7:24 GPT-6 Astra 74:19 GR00T N1.7 11:46 MolmoAct 2 27:11 Pi 0.5 17:56 Rho 31:02
- Mean duration
- Gemini 4 Argon 149.9 s Claude Fable 5.2 165.0 s Claude Opus 5.5 211.6 s DiT-Flow 14.8 s GPT-6 Astra 148.6 s GR00T N1.7 23.5 s MolmoAct 2 54.4 s Pi 0.5 35.9 s Rho 62.1 s
- Success
- Gemini 4 Argon 0% Claude Fable 5.2 53% 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 moving52.6%End-effector moving43.8%Gripper engaged14.2%Contact force > 5 N82.1%Gripper engaged or in contact84.8% Claude Fable 5.2 Share of time manipulating, five definitionsJoints moving83.8%End-effector moving66.4%Gripper engaged98.4%Contact force > 5 N51.1%Gripper engaged or in contact98.8% Claude Opus 5.5 Share of time manipulating, five definitionsJoints moving58.6%End-effector moving42.6%Gripper engaged77.1%Contact force > 5 N82.1%Gripper engaged or in contact94.8% DiT-Flow Share of time manipulating, five definitionsJoints moving88.4%End-effector moving78.2%Gripper engaged74.5%Contact force > 5 N70.0%Gripper engaged or in contact92.5% GPT-6 Astra Share of time manipulating, five definitionsJoints moving68.7%End-effector moving48.4%Gripper engaged54.4%Contact force > 5 N48.7%Gripper engaged or in contact72.9% GR00T N1.7 Share of time manipulating, five definitionsJoints moving97.8%End-effector moving84.6%Gripper engaged51.3%Contact force > 5 N84.9%Gripper engaged or in contact88.7% MolmoAct 2 Share of time manipulating, five definitionsJoints moving94.7%End-effector moving77.2%Gripper engaged63.5%Contact force > 5 N74.2%Gripper engaged or in contact90.0% Pi 0.5 Share of time manipulating, five definitionsJoints moving97.3%End-effector moving92.0%Gripper engaged48.8%Contact force > 5 N74.5%Gripper engaged or in contact88.7% Rho Share of time manipulating, five definitionsJoints moving99.9%End-effector moving95.6%Gripper engaged99.8%Contact force > 5 N78.9%Gripper engaged or in contact99.9%
- 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…
0:003:21