Benchmark · agentic

GDPval

1 hasil 1 model

OpenAI's real-world knowledge-work eval: win/tie rate against industry professionals on 1,320 deliverables across 44 occupations, reported as a percentage. NOT the Artificial Analysis rerun, which is Elo-scored — file that under gdpval-aa.

0 9 18 27 36 2026-08-13 Gemini 3.7 Flash · 34 · 2026-08-13
Gemini 3.7 Flash
Linimasa
Tanggal Model Skor Sumber
2026-08-13 Gemini 3.7 Flash 34.0% Google memperkenalkan Gemini 3.7 Flash dengan kemampuan coding yang lebih baik dan biaya lebih rendah