Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Chart Reasoning on CharXiv Reasoning Questions
Loading...
60.52
Accuracy
Qwen-8B-DeltaThinker
36.3504
42.6252
48.9
55.1748
May 15, 2026
Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen-8B-DeltaThinker
Backbone=Qwen-8B
2026.05
60.52
GLM-9B-DeltaThinker
Backbone=GLM-9B
2026.05
59.1
Bee-8B-RL
Backbone=Bee-8B
2026.05
57
GLM-4.1V-9B-Thinking
Backbone=GLM-4.1V-9B
2026.05
53.76
Qwen3-VL-8B-Thinking
Backbone=Qwen3-VL-8B
2026.05
53.14
ARES-RL-7B
Backbone=ARES-RL-7B
2026.05
43.22
REVisual-R1
Model Family=REVisual
2026.05
41.5
Vision-R1-7B
Backbone=Vision-R1-7B
2026.05
37.28
Feedback
Search any
task
Search any
task