벤치마크 · agentic

GDPval

1 결과 1 모델

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.

Gemini 3.7 Flash

타임라인

날짜	모델	점수	출처
2026-08-13	Gemini 3.7 Flash	34.0%	구글, 코딩 성능 향상 및 비용 절감을 위한 Gemini 3.7 Flash 출시