METR：Research（网页）·· 12 小时前AI 评分61
METR 评测 DeepSeek 与 Qwen 模型：自主能力约相当于 2024 年末前沿水平
DeepSeek and Qwen Evaluation Results June 27, 2025 METR conducted preliminary evaluations of a set of DeepSeek and Qwen models. We found that the level of autonomous capabilities of mid-2025 DeepSeek models is similar to the level of capabilities of frontier models from late 2024. Read more
AI 导读
METR 对 DeepSeek 和 Qwen 共六个模型进行初步评估，发现 2025 年年中的 DeepSeek 模型自主能力水平与 2024 年末的前沿模型相当。
来源：METR：Research（网页） · metr.org