BenchmarkPAW-GEN-10-Agentic
Environmente02Datum-corner alignment
- 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 51:20 Claude Fable 5.2 33:24 Claude Opus 5.5 93:09 DiT-Flow 11:35 GPT-6 Astra 58:08 GR00T N1.7 11:23 MolmoAct 2 7:52 Pi 0.5 6:15 Rho 10:06
- Mean duration
- Gemini 4 Argon 102.7 s Claude Fable 5.2 66.8 s Claude Opus 5.5 186.3 s DiT-Flow 23.2 s GPT-6 Astra 116.3 s GR00T N1.7 22.8 s MolmoAct 2 15.7 s Pi 0.5 12.5 s Rho 20.2 s
- Success
- Gemini 4 Argon 3% Claude Fable 5.2 77% Claude Opus 5.5 0% DiT-Flow 0% GPT-6 Astra 63% GR00T N1.7 0% MolmoAct 2 0% Pi 0.5 0% Rho 0%
- Manipulation density
- Gemini 4 Argon 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% Claude Fable 5.2 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 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 moving100.0%End-effector moving99.5%Gripper engaged0.0%Contact force > 5 N59.6%Gripper engaged or in contact59.6% GPT-6 Astra 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 moving99.9%End-effector moving98.3%Gripper engaged0.0%Contact force > 5 N77.2%Gripper engaged or in contact77.2% MolmoAct 2 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.5%Gripper engaged0.0%Contact force > 5 N90.5%Gripper engaged or in contact90.5% Pi 0.5 Share of time manipulating, five definitionsJoints moving100.0%End-effector moving99.7%Gripper engaged0.0%Contact force > 5 N80.4%Gripper engaged or in contact80.4% Rho Share of time manipulating, five definitionsJoints moving99.8%End-effector moving97.0%Gripper engaged0.0%Contact force > 5 N73.9%Gripper engaged or in contact73.9%
- 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
Held-out benchmark environment
0:001:29