Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GAOKAO-MM Math
Loading...
68.8
Accuracy
DS-R1-Distill-Qwen-32B + GeoTikzBridge-Base
44.048
50.474
56.9
63.326
Mar 24, 2026
Accuracy
Updated 4mo ago
Evaluation Results
Method
Method
Links
Accuracy
DS-R1-Distill-Qwen-32B + GeoTikzBridge-Base
Tikz-supplementation=true
2026.03
68.8
GLM-4.5-Air-106B-A12B + GeoTikzBridge-Base
Tikz-supplementation=true
2026.03
68.8
GLM-Z1-32B + GeoTikzBridge-Base
Tikz-supplementation=true
2026.03
67.5
GLM4.5-V-106B-A12B + GeoTikzBridge-Base
Tikz-supplementation=true
2026.03
66.3
Skywork-OR1-32B + GeoTikzBridge-Base
Tikz-supplementation=true
2026.03
66.3
InternVL3-78B
Tikz-supplementation=f...
2026.03
63.8
InternVL3.5-38B + GeoTikzBridge-Base
Tikz-supplementation=true
2026.03
63.5
GPT-OSS-120B + GeoTikzBridge-Base
Tikz-supplementation=true
2026.03
62.5
Qwen2.5-VL-72B
Tikz-supplementation=f...
2026.03
61.3
GLM4.5-V-106B-A12B
Tikz-supplementation=f...
2026.03
61.3
InternVL3.5-38B
Tikz-supplementation=f...
2026.03
60
Qwen3-VL-30B-A3B + GeoTikzBridge-Base
Tikz-supplementation=true
2026.03
58.8
Qwen3-VL-30B-A3B
Tikz-supplementation=f...
2026.03
55
Qwen3-30B-A3B + GeoTikzBridge-Base
Tikz-supplementation=true
2026.03
55
GPT-4-turbo
Tikz-supplementation=f...
2026.03
50
Qwen2.5-VL-32B
Tikz-supplementation=f...
2026.03
50
GPT-4V
Tikz-supplementation=f...
2026.03
45
Feedback
Search any
task
Search any
task