List your company

Long-horizon web tasks on WebTailBench long-horizon tasks

40.2SR@50Qwen-3-VL-32B
4.8414.0223.232.38May 11, 2026

Evaluation results

MethodLinks
Qwen-3-VL-32BHistory=5, Drop=false2026.0540.229.247.332.915,487
Qwen-3-VL-32BHistory=3, Drop=false2026.0539.629.646.833.412,214
Qwen3-VL-30B-A3BHistory=5, Drop=false2026.053828.844.933.515,456
Qwen3-VL-30B-A3BHistory=3, Drop=false2026.0537.429.144.33412,173
Qwen-3-VL-32BHistory=1, Drop=false2026.0534.827.541.934.34,331
ReVisionHistory=5, Drop=true2026.0532.823.640.227.49,651
Qwen3-VL-30B-A3BHistory=1, Drop=false2026.0532.527.139.234.84,309
Qwen-3-VL-8BHistory=5, Drop=false2026.0530.428.437.13415,392
Qwen-3-VL-8BHistory=3, Drop=false2026.0529.828.736.634.512,089
ReVisionHistory=3, Drop=false2026.0529.628.136.330.311,907
OpenCUAHistory=3, Drop=false2026.0529.528.936.230.212,041
ReVisionHistory=5, Drop=false2026.0529.327.9363015,362
OpenCUAHistory=5, Drop=false2026.0529.128.635.829.815,329
ReVisionHistory=3, Drop=true2026.0528.425.435.229.26,731
Qwen-3-VL-8BHistory=1, Drop=false2026.052626.232.835.34,266
OpenCUAHistory=1, Drop=false2026.0525.829.732.426.44,237
UI-TARS-1.5-7B-DPOHistory=5, Drop=false2026.0518.728.526.833.515,214
UI-TARS-1.5-7B-DPOHistory=3, Drop=false2026.0518.128.822.23411,982
UI-TARS-72B-DPOHistory=5, Drop=false2026.0517.428.119.533.215,376
UI-TARS-72B-DPOHistory=3, Drop=false2026.0516.928.418.233.712,107
UI-TARS-1.5-7B-DPOHistory=1, Drop=false2026.0516.526.620.4354,169
Kimi-VL-A3BHistory=5, Drop=false2026.0515.929.918.13515,438
UI-TARS-72B-DPOHistory=1, Drop=false2026.0515.326.817.434.64,248
Kimi-VL-A3BHistory=3, Drop=false2026.0514.830.316.935.412,217
Kimi-VL-A3BHistory=1, Drop=false2026.0513.2311536.14,318
Qwen2.5-VL-72BHistory=5, Drop=false2026.05930.610.135.715,561
Qwen2.5-VL-7BHistory=5, Drop=false2026.058.630.710.13615,361
Qwen2.5-VL-72BHistory=3, Drop=false2026.058.2319.436.212,244
Qwen2.5-VL-7BHistory=3, Drop=false2026.057.931.19.236.512,067
Qwen2.5-VL-32BHistory=5, Drop=false2026.057.5318.636.115,472
Qwen2.5-VL-72BHistory=1, Drop=false2026.057.531.78.636.94,349
Qwen2.5-VL-32BHistory=3, Drop=false2026.056.831.47.936.812,183
Qwen2.5-VL-7BHistory=1, Drop=false2026.056.531.87.837.24,213
Qwen2.5-VL-32BHistory=1, Drop=false2026.056.232.17.137.44,287