BenchmarkPAW-GEN-10-Agentic
Environmente03Pour screws into the funnel
- Episodes
- GPT-6 Astra 30 Claude Fable 5.2 30 Claude Opus 5.5 30 DiT-Flow 30 Gemini 4 Argon 30 GR00T N1.7 30 MolmoAct 2 30 Pi 0.5 30 Rho 30
- Total duration
- GPT-6 Astra 27:33 Claude Fable 5.2 26:09 Claude Opus 5.5 26:54 DiT-Flow 8:54 Gemini 4 Argon 19:37 GR00T N1.7 2:53 MolmoAct 2 4:18 Pi 0.5 5:38 Rho 2:52
- Mean duration
- GPT-6 Astra 55.1 s Claude Fable 5.2 52.3 s Claude Opus 5.5 53.8 s DiT-Flow 17.8 s Gemini 4 Argon 39.2 s GR00T N1.7 5.8 s MolmoAct 2 8.6 s Pi 0.5 11.3 s Rho 5.7 s
- Success
- GPT-6 Astra 83% Claude Fable 5.2 90% Claude Opus 5.5 93% DiT-Flow 0% Gemini 4 Argon 97% GR00T N1.7 3% MolmoAct 2 13% Pi 0.5 17% Rho 3%
- Manipulation density
- GPT-6 Astra Share of time manipulating, five definitionsJoints moving87.2%End-effector moving70.4%Gripper engaged59.9%Contact force > 5 N69.3%Gripper engaged or in contact77.1% Claude Fable 5.2 Share of time manipulating, five definitionsJoints moving92.4%End-effector moving70.0%Gripper engaged58.9%Contact force > 5 N36.3%Gripper engaged or in contact73.2% Claude Opus 5.5 Share of time manipulating, five definitionsJoints moving91.7%End-effector moving81.5%Gripper engaged64.2%Contact force > 5 N59.6%Gripper engaged or in contact80.7% DiT-Flow Share of time manipulating, five definitionsJoints moving99.8%End-effector moving98.3%Gripper engaged74.8%Contact force > 5 N46.0%Gripper engaged or in contact84.6% Gemini 4 Argon Share of time manipulating, five definitionsJoints moving88.7%End-effector moving78.6%Gripper engaged62.0%Contact force > 5 N78.4%Gripper engaged or in contact87.2% GR00T N1.7 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.3%Gripper engaged66.4%Contact force > 5 N59.8%Gripper engaged or in contact80.9% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.5%Gripper engaged60.6%Contact force > 5 N55.4%Gripper engaged or in contact75.3% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.6%Gripper engaged80.5%Contact force > 5 N46.3%Gripper engaged or in contact87.0% Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.1%Gripper engaged71.5%Contact force > 5 N60.8%Gripper engaged or in contact79.9%
- SPARC smoothness
- 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. 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. 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. 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…
0:000:52