精选理由
DeepSeek V4 Pro在成本和性能上优于Fable 5，值得一试。
DeepSeek V4 Pro在Fireworks上表现优异，在SWE-Bench和LiveCodeBench上击败Fable 5，每解决一个任务的成本仅为Fable 5的三分之一，且不拒绝合法的安全审查工作。
原文 · Fireworks AI
Your closed model refused a task it should have done. Ours didn't. DeepSeek V4 Pro on Fireworks: b...
Your closed model refused a task it should have done. Ours didn't. DeepSeek V4 Pro on Fireworks: beats Fable 5 on SWE-Bench and LiveCodeBench, a third of the cost per solved task, and it doesn't decline legitimate security-review work. Read more: fireworks.ai/blog/DeepSeekV… 💬 0 🔄 1 ❤️ 5 👀 537 📊 1 ⚡