Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Real-world perception-centric reasoning on HRBench 4K (test)
Loading...
80.25
Accuracy
GLM-9B-DeltaThinker
59.346
64.773
70.2
75.627
May 15, 2026
Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
GLM-9B-DeltaThinker
Algorithm=DeltaPrompts
2026.05
80.25
Qwen-8B-DeltaThinker
Algorithm=DeltaPrompts
2026.05
77.25
Vision-R1-7B
2026.05
75.38
GLM-4.1V-9B-Thinking
2026.05
73.75
Qwen3-VL-8B-Thinking
2026.05
72.22
ARES-RL-7B
2026.05
72.13
REVisual-R1
2026.05
71.88
Bee-8B-RL
2026.05
60.15
Feedback
Search any
task
Search any
task