List your company

Robotic Vision-Language Tasks on RoboStressBench

58.1Overall AccuracyQwen3.5
28.77236.3864451.614May 30, 2026

Evaluation results

MethodLinks
Qwen3.5Size=35B-A3B2026.0558.166.56964.660.745.356.673.256.769.13827.145.861.87155.359.250.342.57962.992.9
Qwen3.5Size=27B2026.055865.36666.465.946.364.673.253.468.938.227.644.463.571.360.156.757.244.977.163.377
Qwen3.6Size=27B2026.0557.363.364.568.860.749.160.473.250.868.739.228.342.559.670.657.655.254.74578.367.168.8
Qwen3VLSize=30B-A3B2026.0555.964.76563.365.242.257.170.856.267.936.325.241.658.264.550.35839.441.171.968.699.8
Qwen3.6Size=35B-A3B2026.0555.863.766.662.651.844.660.874.155.270.136.425.442.558.871.353.45852.139.778.167.181.1
Qwen3.5Size=9B2026.0550.761.560.460.341.640.854.769.554.263.131.423.439.75066.651.653.645.237.873.758.965.5
Qwen3.5Size=4B2026.0549.859.459.161.547.340.449.565.651.661.932.322.437.942.666.445.950.839.437.172.659.668.8
Qwen3VLSize=8B2026.0549.758.957.659.94938.452.469.845.862.833.321.536.948.666.646.65345.336.273.458.864.2
GPT-5.5Size=–2026.0546.253.558.358.839.131.15062.847.458.326.921.833.154.465.941.853.454.630.580.338.957
Gemini-3.1Size=–2026.0544.848.851.851.845.731.142.957.548.558.728.827.331.145.654.144.346.64733.27041.656.3
Qwen3VLSize=4B2026.0543.250.649.853.74432.438.16236.653.427.916.830.634.557.738.445.634.131.965.249.453.8
Molmo2Size=8B2026.0535.24748.12916.929.54152.542.150.810.914.727.536.358.137.641.436.518.163.639.254.3
InternVL3.5Size=8B2026.0532.943.645.126.513.628.142.554.336.146.98.612.424.333.559.137.83733.912.867.941.550.3
InternVL3.5Size=4B2026.0532.141.244.527.613.428.340.65532.745.59.511.723.227.259.534.237.632.513.665.241.146.2
Molmo2Size=4B2026.0531.53942.624.913.626.536.351.631.746.19.713.323.632.156.733.838.236.712.862.940.344.5
InternVL3.5Size=14B2026.0529.937.841.724.511.824.837.353.431.942.79.51219.826.455.828.235.429.59.267.64045.9