GPT-6.2 Astra 与 Sol 上线 Perplexity,WANDR 基准成绩提升
Perplexity 把 OpenAI 的两个 GPT-6.2 模型接进自家搜索和 Computer,还公布了 WANDR 评测:Sol 一个任务才 $2.65,分数只比贵四倍的 Astra 低一点。跑深度研究的开发者可以按预算选了。
Perplexity 宣布 GPT-6.2 Astra 和 GPT-6.2 Sol 已接入 Perplexity Search 与 Computer。在内部 WANDR(Wide-and-Deep-Research)基准上,GPT-6.2 Astra 得分 0.783,单任务成本约 $12.54,较 GPT-6 Astra 提升 0.095;GPT-6.2 Sol 得分 0.746,单任务成本约 $2.65,较 GPT-6.1 Sol 提升 0.065。
WANDR 是 Perplexity 衡量宽域与深度研究任务表现的基准,本次两个模型在得分和成本之间呈现明显分层:Astra 高分高价,Sol 以约五分之一的价格拿到 0.746 的成绩。Perplexity CEO Arav Srinivas 通过 X 平台发布了这组评测数据。
对开发者而言,GPT-6.2 Sol 的性价比组合更适合大批量自动化研究任务,Astra 则面向对结果质量更敏感的场景。两款模型现已可直接在 Perplexity 产品内调用。
Astra and Sol 6.2 evals on Perplexity. Good improvements on Wide-and-Deep-Research performance Perplexity @perplexity_ai GPT-6.2 Astra and GPT-6.2 Sol are now available in Perplexity Search and Computer. On our WANDR benchmark, GPT-6.2 Astra scored 0.783 at about $12.54 per task, up 0.095 from GPT-6 Astra. GPT-6.2 Sol hit 0.746 at about $2.65, up 0.065 from GPT-6.1 Sol. 🔗 View Quoted Tweet📊 3 ⚡
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows and US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include Perplexity, GPT-6.2, Astra, Sol.
Source attribution: curated from Aravind Srinivas (@AravSrinivas). Cross-source corroboration: 11 independent sources have covered this development (including Perplexity, OpenAI Blog, lmarena.ai), confirming industry-wide signal strength.