Perplexity:DRACO深度研究能力的跨领域基准测试 episode artwork

EPISODE · Apr 7, 2026 · 23 MIN

Perplexity:DRACO深度研究能力的跨领域基准测试

from 每日AI · host 每日新闻

DRACO是一个由 Perplexity 开发的、旨在评估 AI 系统深度研究能力的跨领域基准测试。该基准包含 100 个复杂的开放式任务,涵盖了金融、医疗和法律等 10 个专业领域,并涉及全球 40 个国家的信息源。任务素材源自真实的匿名用户查询,经过系统化的脱敏、重构与增强,以确保其具备客观的可评价性和高度的挑战性。为了实现精准评估,研究团队与各界专家合作制订了详细的评分细则,从事实准确性、分析深度、呈现质量及引用规范四个维度进行衡量。实验结果表明,Perplexity Deep Research 在各项指标上均优于 OpenAI 和 Google 的同类系统,展现了强大的智能体编排与信息整合能力。该基准测试已向开源社区开放,旨在推动大模型在处理高强度科研与专业分析任务时的透明度与准确性。

Episode metadata supplied by the publisher feed · Published Apr 7, 2026

Embed this episode

Ready to play

Perplexity:DRACO深度研究能力的跨领域基准测试

0:00 23:23

No transcript for this episode yet

We transcribe on demand. Request one and we'll notify you when it's ready — usually under 10 minutes.

No similar episodes found.

Frequently Asked Questions

How long is this episode of 每日AI?

This episode is 23 minutes long.

When was this 每日AI episode published?

This episode was published on April 7, 2026.

Can I download this 每日AI episode?

Yes. Use the download control on the episode player to save the publisher-provided media file.
URL copied to clipboard!