List your company

Object classification on TEA (test)

74.48AccuracyHuman
2.116820.903439.6958.4766Feb 5, 2026

Evaluation results

MethodLinks
Human2026.0274.48—
o3-20252026.0241.96—
GPT-52026.0240.56—
GPT-4.12026.0235.66—
Gemini-2.5-Pro2026.0233.57—
Gemini-2.5-Flash2026.0232.17—
llama-4-Scout2026.0230.07—
GPT-4o2026.027.69—
Claude-Opus-42026.024.9—