Benchmark · agentic

GDPval

1 条结果 1 个模型

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

时间线

日期	模型	得分	来源
2026-08-13	Gemini 3.7 Flash	34.0%	Google推出Gemini 3.7 Flash，提升编码能力并降低成本