List your company

GUI Navigation on OSWorld Verified

91.7OS Success RateVLAA-GUI w/ Gemini 3 Flash
59.907268.161176.41584.6689Apr 23, 2026

Evaluation results

MethodLinks
VLAA-GUI w/ Gemini 3 FlashStep Budget=1002026.0491.764.974.8567.3363.468.77
VLAA-GUI w/ Opus 4.6Step Budget=1002026.0491.782.8775.1783.6765.677.45
VLAA-GUI w/ Opus 4.5 + MAI-UIStep Budget=1002026.0491.6784.2672.7783.6761.0976.26
VLAA-GUI w/ Opus 4.5Step Budget=152026.0487.557.1659.6971.4345.258.58
VLAA-GUI w/ Opus 4.5Step Budget=502026.0487.575.9771.3879.5955.671
HIPPO w/ Opus 4.5Step Budget=1002026.0487.574.2769.2795.9264.3174.49
VLAA-GUI w/ Opus 4.5Step Budget=1002026.0487.579.3876.5781.636174.89
VLAA-GUI w/ Gemini 3.1 ProStep Budget=152026.0483.352.9954.3361.2234.751.69
VLAA-GUI w/ Sonnet 4.6Step Budget=152026.0483.369.7258.7257.1360.264.13
VLAA-GUI w/ Opus 4.6Step Budget=152026.0483.360.6566.3879.5955.964.75
VLAA-GUI w/ Gemini 3 FlashStep Budget=502026.0483.369.1962.7562.495163.14
VLAA-GUI w/ Gemini 3.1 ProStep Budget=502026.0483.371.5167.3267.3555.966.8
VLAA-GUI w/ Sonnet 4.6Step Budget=502026.0483.379.2369.2457.1366.771.11
VLAA-GUI w/ Opus 4.6Step Budget=502026.0483.378.672.683.6761.373.85
VLAA-GUI w/ Gemini 3.1 ProStep Budget=1002026.0483.376.673.7673.4762.972.47
VLAA-GUI w/ Sonnet 4.6Step Budget=1002026.0483.379.2469.2557.1468.871.67
VLAA-GUI w/ Gemini 3 FlashStep Budget=152026.0479.229.9254.1457.133443.15
GTA1 w/ GPT-5Step Budget=1002026.0479.1763.9162.5679.5950.9163.41
OS-Symphony w/ GPT-5Step Budget=1002026.0479.1765.7367.7669.2357.9865.84
EvoCUAStep Budget=502026.0478.2659.7164.5581.6327.8956.73
Agent S3 w/ GPT-5Step Budget=1002026.0477.566.4661.2369.851.3762.63
OS-Symphony w/ GPT-5Step Budget=502026.047564.8561.1969.2354.8663.61
CoAct-1 w/ GPT-5Step Budget=1002026.047562.9357.9471.4347.8759.93
Agent S3 w/ Opus 4.5Step Budget=1002026.047576.0667.5159.185967.46
UiPath w/ GPT-5Step Budget=502026.0473.9149.5262.1271.4337.353.69
Kimi K2.5Step Budget=1002026.0473.9169.1166.4263.4746.1163.34
CoACT-1 w/ GPT-5Step Budget=502026.0470.8360.6554.0969.3942.3756.39
Claude-Sonnet-4.5Step Budget=1002026.0470.8372.5961.3563.2749.5462.84
UiPath w/ Opus 4.5Step Budget=1002026.0470.8374.1368.3373.4752.9767.14
Seed-1.8Step Budget=1002026.0466.6768.867.0571.4342.3861.87
DeepMiner-Mano-72BStep Budget=1002026.0466.6763.2252.5183.6724.4153.91
OpenCUA-72BStep Budget=1002026.0461.1344.7349.9572.5822.1644.91