List your company

Scene understanding on 40 harbor scenes 1.0 (test)

5.69Latency (s)gpt-4.1
3.548818.001932.45546.9081Dec 30, 2025

Evaluation results

MethodLinks
gpt-4.1Model=gpt-4.12025.125.6983838384
gpt-5-minimalModel=gpt-5, variant=minimal2025.127.0783.3828286
gpt-5-lowModel=gpt-5, variant=low2025.1217.2184.5858186
gpt-5-mediumModel=gpt-5, variant=medium2025.1230.0486.6878588
gpt-5-highModel=gpt-5, variant=high2025.1259.2286.6878587