Share your thoughts, 1 month free Claude Pro on usSee more

Real-world perception-centric reasoning on RealWorldQA (test)

77.04Accuracy

GLM-9B-DeltaThinker

Updated 16d ago

Evaluation Results

Method	Links
GLM-9B-DeltaThinker 2026.05		77.04
Qwen-8B-DeltaThinker 2026.05		75.82
Qwen3-VL-8B-Thinking 2026.05		73.07
GLM-4.1V-9B-Thinking 2026.05		72.19
Bee-8B-RL 2026.05		72.03
Vision-R1-7B 2026.05		67.58
ARES-RL-7B 2026.05		66.67
REVisual-R1 2026.05		64.36