ModelsMulti-source

GPT-6.2 Sol (Max) 以 $0.90 中位成本刷新 Agent Arena 帕累托前沿

Why we picked it

OpenAI 新发的 GPT-6.2 Sol 把智能体任务的中位成本压到 $0.90,比同分的老款便宜 13%,比分数略高的 Astra 便宜 69%。跑大批量 Agent 任务、对 API 成本敏感的团队可以看看这份榜单再选型号。

OpenAI 的 GPT-6.2 Sol (Max) 在 Agent Arena 排行榜上重塑了性能与成本的帕累托前沿,中位成本为每任务 $0.90。

Body

与上一代 GPT-6.1 Sol (Max) 相比,新模型以 1241 分持平排名(#12),但中位成本低 13%($0.90 对 $1.04)。同代兄弟型号 GPT-6.2 Astra (Max) 排名更高(#6),但分数多约 50 分的同时中位成本达 $2.94,Sol 的成本比它低 69%。

这一成绩将 GPT-6.2 Sol 定位为 Agent Arena 上低成本档位的优选,适合对每任务成本敏感的智能体部署场景。

Original · lmarena.ai

GPT-6.2 Sol (Max) has reshaped the Agent Arena Pareto frontier at $0.90 median cost per task! Compared with: - #12 GPT-6.1 Sol (Max): Coming in tied at 1241 pts at 13% lower median cost per task ($0.90 vs. $1.04) - #6 GPT-6.2 Astra (Max): 50 fewer pts at 69% lower median cost per task ($0.90 vs. $2.94)📊 2 ⚡

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include GPT-6.2 Sol, OpenAI, Agent Arena, reasoning models.

Source attribution: curated from lmarena.ai (@lmarena_ai). Cross-source corroboration: 11 independent sources have covered this development (including TestingCatalog, @koltregaskes, OpenAI), confirming industry-wide signal strength.