BenchmarkPAW-GEN-10
Environmente02Datum-corner alignment
- Episodes
- Pi 0.5 30 Claude Fable 5.2 (D10) 30 Claude Opus 5.5 (D10) 30 DiT-Flow 30 Gemini 4 Argon (D10) 30 GPT-6 Astra (D10) 30 GR00T N1.7 30 MolmoAct 2 30 Rho 30
- Total duration
- Pi 0.5 10:48 Claude Fable 5.2 (D10) 33:24 Claude Opus 5.5 (D10) 93:09 DiT-Flow 11:36 Gemini 4 Argon (D10) 51:20 GPT-6 Astra (D10) 58:08 GR00T N1.7 11:31 MolmoAct 2 9:37 Rho 10:25
- Mean duration
- Pi 0.5 21.6 s Claude Fable 5.2 (D10) 66.8 s Claude Opus 5.5 (D10) 186.3 s DiT-Flow 23.2 s Gemini 4 Argon (D10) 102.7 s GPT-6 Astra (D10) 116.3 s GR00T N1.7 23.0 s MolmoAct 2 19.2 s Rho 20.8 s
- Success
- Pi 0.5 0% Claude Fable 5.2 (D10) 77% Claude Opus 5.5 (D10) 0% DiT-Flow 0% Gemini 4 Argon (D10) 3% GPT-6 Astra (D10) 63% GR00T N1.7 0% MolmoAct 2 23% Rho 7%
- Manipulation density
- Pi 0.5 Share of time manipulating, five definitionsJoints moving98.9%End-effector moving91.2%Gripper engaged0.0%Contact force > 5 N57.3%Gripper engaged or in contact57.3% Claude Fable 5.2 (D10) Share of time manipulating, five definitionsJoints moving92.3%End-effector moving81.6%Gripper engaged58.4%Contact force > 5 N78.2%Gripper engaged or in contact84.4% Claude Opus 5.5 (D10) Share of time manipulating, five definitionsJoints moving40.4%End-effector moving32.7%Gripper engaged0.0%Contact force > 5 N72.9%Gripper engaged or in contact72.9% DiT-Flow Share of time manipulating, five definitionsJoints moving97.8%End-effector moving92.3%Gripper engaged0.0%Contact force > 5 N31.7%Gripper engaged or in contact31.7% Gemini 4 Argon (D10) Share of time manipulating, five definitionsJoints moving28.9%End-effector moving25.3%Gripper engaged0.0%Contact force > 5 N71.4%Gripper engaged or in contact71.4% GPT-6 Astra (D10) Share of time manipulating, five definitionsJoints moving76.1%End-effector moving60.7%Gripper engaged0.0%Contact force > 5 N75.4%Gripper engaged or in contact75.4% GR00T N1.7 Share of time manipulating, five definitionsJoints moving98.5%End-effector moving92.8%Gripper engaged0.0%Contact force > 5 N61.2%Gripper engaged or in contact61.2% MolmoAct 2 Share of time manipulating, five definitionsJoints moving99.3%End-effector moving91.6%Gripper engaged0.0%Contact force > 5 N66.9%Gripper engaged or in contact66.9% Rho Share of time manipulating, five definitionsJoints moving99.6%End-effector moving94.9%Gripper engaged0.0%Contact force > 5 N49.1%Gripper engaged or in contact49.1%
- SPARC smoothness
- 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. Claude Fable 5.2 (D10) 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 (D10) 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 (D10) 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 (D10) 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. 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
0:000:23