AI 导读
每任务成本差异巨大，Anthropic 表现最佳的模型每任务成本在 $0.3 到 $1 之间——最高可达 Kimi K3 成本的约 6 倍，而 Kimi K3 在 MLCR-AA Score 与每任务成本的帕累托前沿上位于近期 Claude 模型之后。虽然 OpenAI 的 GPT-5.6 系列因完整性较低而未登顶分数榜，但其强劲的准确率伴随着相对更低的成本，GPT-5.6 Terra 和 Luna 均位于帕累托前沿上。
正文
Cost per task varies widely, with top performing models from Anthropic ranging from $0.3 to $1 per task - this is up to ~6x higher than the cost of Kimi K3, which sits behind the recent Claude models on the MLCR-AA Score vs. Cost per Task Pareto frontier. While OpenAI’s GPT-5.6 family does not top scores due to low completeness, their strong accuracy comes with relatively lower cost and both GPT-5.6 Terra and Luna sit on the Pareto frontier.
来源：@ArtificialAnlys · x.com