List your company

Geometric Reasoning on GeoAux-Bench-Core Curriculum Senior

83.91AccuracyGemini-2.5-Pro
3.715624.535345.35566.1747Mar 19, 2026

Evaluation results

MethodLinks
Gemini-2.5-ProThink=true2026.0383.91
Gemini-2.5-FlashThink=true2026.0380.1
GPT-5Think=true2026.0371.48
Qwen3-VL-235B-Thk.Think=true2026.0364.68
Doubao-seed-1.6Think=true2026.0362.02
Qwen3-VL-235B-Ins.Think=false2026.0361.36
Qwen3-VL-30B-Ins.Think=false2026.0361.36
Claude-Opus-4.1Think=true2026.0360.36
Claude-Sonnet-4.5Think=true2026.0359.2
Qwen3-VL-30B-Thk.Think=true2026.0355.72
MiMo-VL-7B-RLThink=true2026.0350.75
MiMo-VL-7B-SFTThink=false2026.0350.41
GLM-4.5VThink=false2026.0345.27
InternVL3.5-8BThink=false2026.0338.31
GLM-4.1V-Thk.Think=true2026.0331.67
InternVL3-8BThink=false2026.0325.87
Qwen2.5-VL-Ins.Think=false2026.0323.05
GPT-4oThink=false2026.0319.57
MathCanvas-7BThink=false2026.0318.41
BAGEL-7B-MoTThink=false2026.037.3
BAGEL-Zebra-CoTThink=false2026.036.8