AI模型精选76°

Qwen 3.7-Max 在智能体任务中击败 Opus 4.7 和 GPT-5.5

Qwen 3.7-max beats Opus 4.7 and GPT-5.5 We tested…

精选理由

做智能体开发或自动化任务的团队,Qwen 3.7-Max 在成本与性能上碾压对手,值得在类似场景中直接替换测试。

AI 摘要

在编写自训练俄罗斯方块机器人的真实智能体任务中,Qwen 3.7-Max 以 56% 的改进幅度、仅 1.32 美元的训练成本,全面超越 Claude Opus 4.7(+28%,12.15 美元)和 GPT-5.5(+7%,2.85 美元)。测试中每个模型可读取自身代码、运行基准测试并迭代重写 10 轮。Qwen 3.7-Max 在性能提升和成本效率上均占优,成本仅为 Claude 的 1/9、GPT 的 1/2。这表明 Qwen Max 在长智能体循环任务中具有显著优势。

原文 · @atomic_chat_hq

Qwen 3.7-max beats Opus 4.7 and GPT-5.5 We tested…

Qwen 3.7-max beats Opus 4.7 and GPT-5.5

We tested three frontier models on a real agentic task: write a Tetris bot that plays the game and trains itself. Each model could read its own code, run benchmarks, and rewrite itself across 10 iterations. Then we compared the final bots head to head.

Qwen 3.7-Max: training cost $1.32, bot improvement +56% Claude Opus 4.7: training cost $12.15, bot improvement +28% GPT-5.5: training cost $2.85, bot improvement +7%

Qwen won on every dimension - biggest jump, 9× cheaper than Claude, 2× cheaper than GPT. Long agentic loops is where Qwen Max actually delivers.