List your company

GUI Knowledge Evaluation on GUI Knowledge Benchmark

83.03State ScoreO3
48.200457.242766.28575.3273May 27, 2026

Evaluation results

MethodLinks
O32026.0583.0384.1288.3974.8375.9845.7569.4595.4773.3
Gemini-2.5-Pro2026.0581.1984.3687.171.0373.2546.9767.7292.5671.69
GPT-5-Chat2026.0578.984.1288.3971.5571.5543.8568.9891.2670.97
Claude-Sonnet-4.52026.0574.7781.5282.5849.8370.1943.3370.391.5666.53
GUI-CIDER-8BParameters=8B2026.0572.6175.8380.1361.5565.4246.4571.8180.5866.51
Doubao-V-Pro2026.0572.4883.6581.2967.2475.6441.0733.0794.1763.42
Claude-Sonnet-42026.0570.1878.4478.0641.962.5242.1165.294.8262.16
Qwen2.5-VL-72BParameters=72B2026.0569.2777.498061.7264.9138.9962.285.4463.88
Qwen3-VL-8B-InstructParameters=8B2026.0566.9776.379.3560.8663.5445.0671.0278.9665.23
GUI-owl-7BParameters=7B2026.0560.0964.9363.2321.5555.3736.0521.2639.8140.74
Qwen2.5-VL-7BParameters=7B2026.0553.2167.776051.7250.639.3416.2248.8745.16
UI-TARS-1.5-7BParameters=7B2026.0549.5459.4859.3522.2459.1134.3238.7455.3444.27
GLM-4.52026.0549.5448.153.5527.0717.5535.5328.9891.9138.1