Trending storyPast story
Fireworks AI launches FireRouter: the frontier isn't a model, it's a router
1 report1 sourceupdated 7 days ago
What happened
Summary
Fireworks AI 在 DeepSWE 编程基准上测了 18 个模型，发现按任务挑模型比死用一个强得多。单用最强的 GPT-6 Astra 能解决 74.1% 的任务，每次成本 6.52 美元；但一个“事后诸葛亮”路由器从 18 个模型里给每个任务挑最合适的，解决率能到 97.6%，成本反而降到 1.88 美元。只用开源模型也能到 90.3%，成...
Coverage
Follow the reports to see the story from different sides.
Sep 21
- AI HOT (Curated Pool)PickFireworks AI launches FireRouter: the frontier isn't a model, it's a router
Fireworks AI benchmarked 18 models on DeepSWE: picking the right model per task beats any single model. GPT-6 Astra alone scores 74.1% at $6.52/task. An oracle router across all 18 hits 97.6% at $1.88. Open-weight models alone reach 90.3% at $1.45. 94 of 113 tasks need a model under $3; the three priciest models are the best pick on only 3 tasks. FireRouter aims to make that per-task choice before the work starts—the post doesn't yet detail how.