List your company

Mathematical Reasoning on MathVista (Detailed Accuracy)

88.9Accuracy (All)GLM-4.5-Air-106B-A12B + GeoTikzBridge-Base
17.24435.84754.4573.053Jan 5, 2026Jan 18, 2026Jan 31, 2026Feb 13, 2026Feb 26, 2026Mar 11, 2026Mar 24, 2026

Evaluation results

MethodLinks
GLM-4.5-Air-106B-A12B + GeoTikzBridge-BaseTikz-supplementation=true2026.0388.9—————
GPT-OSS-120B + GeoTikzBridge-BaseTikz-supplementation=true2026.0388—————
GLM-Z1-32B + GeoTikzBridge-BaseTikz-supplementation=true2026.0387.5—————
Skywork-OR1-32B + GeoTikzBridge-BaseTikz-supplementation=true2026.0386.1—————
Qwen3-30B-A3B + GeoTikzBridge-BaseTikz-supplementation=true2026.0385.6—————
DS-R1-Distill-Qwen-32B + GeoTikzBridge-BaseTikz-supplementation=true2026.0384.1—————
Doubao-pro-1.52026.0179.577.788.98682.362
COGFLOW-7BParameters=7B2026.0176.870.493.173.786.959.3
GLM4.5-V-106B-A12B + GeoTikzBridge-BaseTikz-supplementation=true2026.0376.4—————
Qwen3-VL-30B-A3B + GeoTikzBridge-BaseTikz-supplementation=true2026.0374.5—————
GLM4.5-V-106B-A12BTikz-supplementation=false2026.0374.5—————
VL-RethinkerParameters=7B2026.0173.7—————
GeminiVersion=2.0-Flash2026.0173.4—————
ReVisual-R12026.0173.1—————
InternVL3.5-38B + GeoTikzBridge-BaseTikz-supplementation=true2026.0371.8—————
WeThink2026.0170.9—————
Qwen3-VL-30B-A3BTikz-supplementation=false2026.0369.7—————
X-REASONER2026.0169—————
InternVL3.5-38BTikz-supplementation=false2026.0368.8—————
Claude 3.5 Sonnet2026.0167.7—————
InternVL3-78BTikz-supplementation=false2026.0366.3—————
Qwen2.5-VL-32BTikz-supplementation=false2026.0365.4—————
GPT-4oTikz-supplementation=false2026.0364.7—————
Claude3.5-SonnetTikz-supplementation=false2026.0364.4—————
Qwen2.5-VL-72BTikz-supplementation=false2026.0364.4—————
GPT-4o2026.0163.8—————
Skywork-R1VParameters=38B2026.0160.6—————
Gemini-1.5-ProTikz-supplementation=false2026.0358.9—————
GPT-4-turboTikz-supplementation=false2026.0358.3—————
GPT-4VTikz-supplementation=false2026.0350.5—————
MultiMathParameters=7B2026.015040.166.861.85033
GPT-4V2026.0149.943.150.557.565.238
GeminiVersion=1.0-Pro2026.0147.748.335.150.565.842.5
SVE-MathParameters=7B2026.0137.431.953.92941.430.8
SPHINX-Plus2026.0136.754.616.423.141.843
VCAR2026.0133.730.934.638.737.328.5
LLaVA-1.5Parameters=13B2026.0126.819.720.218.845.636.9
TinyLLaVAParameters=3B2026.0126.720.419.723.144.931.8
G-LLaVAParameters=7B2026.0125.119.148.73.62528.7
LLaMA-Adapter-V2Parameters=7B2026.0123.921.225.511.332.331.8
MiniGPT-v2Parameters=7B2026.0123.118.62613.430.430.2
mPLUG-Owl2Parameters=7B2026.0122.222.723.610.227.227.9
LLaVA-1.5Parameters=7B2026.012022.77.711.826.633