BenchmarkPAW-GEN-10
Environmente06Put tools in standing toolbox
- Episodes
- MolmoAct 2 30 Claude Fable 5.2 30 Claude Opus 5.5 30 DiT-Flow 30 Gemini 4 Argon 30 GPT-6 Astra 30 GR00T N1.7 30 Pi 0.5 30 Rho 30
- Total duration
- MolmoAct 2 12:04 Claude Fable 5.2 59:02 Claude Opus 5.5 43:30 DiT-Flow 37:08 Gemini 4 Argon 50:15 GPT-6 Astra 24:46 GR00T N1.7 11:12 Pi 0.5 14:52 Rho 1:19
- Mean duration
- MolmoAct 2 24.1 s Claude Fable 5.2 118.1 s Claude Opus 5.5 87.0 s DiT-Flow 74.3 s Gemini 4 Argon 100.5 s GPT-6 Astra 49.5 s GR00T N1.7 22.4 s Pi 0.5 29.7 s Rho 2.6 s
- Success
- MolmoAct 2 0% Claude Fable 5.2 30% Claude Opus 5.5 0% DiT-Flow 0% Gemini 4 Argon 0% GPT-6 Astra 0% GR00T N1.7 0% Pi 0.5 0% Rho 0%
- Manipulation density
- MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving95.8%Gripper engaged76.9%Contact force > 5 N78.5%Gripper engaged or in contact95.4% Claude Fable 5.2 Share of time manipulating, five definitionsJoints moving77.7%End-effector moving56.0%Gripper engaged87.2%Contact force > 5 N46.7%Gripper engaged or in contact92.6% Claude Opus 5.5 Share of time manipulating, five definitionsJoints moving86.0%End-effector moving68.2%Gripper engaged37.2%Contact force > 5 N89.3%Gripper engaged or in contact93.1% DiT-Flow Share of time manipulating, five definitionsJoints moving96.1%End-effector moving84.4%Gripper engaged99.9%Contact force > 5 N38.9%Gripper engaged or in contact100.0% Gemini 4 Argon Share of time manipulating, five definitionsJoints moving33.8%End-effector moving23.8%Gripper engaged32.6%Contact force > 5 N64.8%Gripper engaged or in contact71.3% GPT-6 Astra Share of time manipulating, five definitionsJoints moving60.2%End-effector moving41.3%Gripper engaged14.0%Contact force > 5 N52.3%Gripper engaged or in contact62.8% GR00T N1.7 Share of time manipulating, five definitionsJoints moving99.9%End-effector moving96.2%Gripper engaged99.6%Contact force > 5 N74.3%Gripper engaged or in contact99.8% Pi 0.5 Share of time manipulating, five definitionsJoints moving99.9%End-effector moving98.4%Gripper engaged17.5%Contact force > 5 N65.9%Gripper engaged or in contact71.3% Rho Share of time manipulating, five definitionsJoints moving100.0%End-effector moving98.0%Gripper engaged0.0%Contact force > 5 N66.0%Gripper engaged or in contact66.0%
- SPARC smoothness
- 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. 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. 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. 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
0:000:15