List your company

Geometric Reasoning on GeoAux-Bench-Core Olympiad Senior

89.45AccuracyQwen3-VL-235B-Thk.
29.33844.94460.5576.156Mar 19, 2026

Evaluation results

MethodLinks
Qwen3-VL-235B-Thk.Think=true2026.0389.45
Qwen3-VL-30B-Thk.Think=true2026.0383.97
Gemini-2.5-ProThink=true2026.0382.28
GPT-5Think=true2026.0379.32
Qwen3-VL-235B-Ins.Think=false2026.0378.9
Qwen3-VL-30B-Ins.Think=false2026.0375.53
Doubao-seed-1.6Think=true2026.0372.57
GLM-4.5VThink=false2026.0372.15
MiMo-VL-7B-SFTThink=false2026.0371.73
MiMo-VL-7B-RLThink=true2026.0371.73
InternVL3-8BThink=false2026.0367.93
Qwen2.5-VL-Ins.Think=false2026.0365.82
Gemini-2.5-FlashThink=true2026.0364.56
Claude-Opus-4.1Think=true2026.0358.23
GPT-4oThink=false2026.0357.38
GLM-4.1V-Thk.Think=true2026.0356.12
Claude-Sonnet-4.5Think=true2026.0355.7
InternVL3.5-8BThink=false2026.0354.85
MathCanvas-7BThink=false2026.0346.84
BAGEL-7B-MoTThink=false2026.0334.6
BAGEL-Zebra-CoTThink=false2026.0331.65