DeepSeek V4.1 Flash-1017 编程基准超越 GPT-5.6 Sol，价格低一个量级
DeepSeek 新版开源模型，编程基准打平或超过 Opus 5，价格却只有零头，想省 API 成本的可以看看测试细节。
DeepSeek 发布 V4.1 Flash-1017，在部分编程和智能体基准上超过 GPT-5.6 Sol 和 Claude Opus 5：DeepSWE 得分 77.0，高于 GPT-5.6 Sol 的 73.0 和 Opus 5 的 74.0；Automation-Bench 得分 60.5，同样领先两家。价格方面，输入/输出为 $0.15/$0.60（错峰），远低于 GPT-5.6 Sol 的 $4/$20 和 Opus 5 的 $5/$25。模型采用 MIT 许可开源，支持 1M token 上下文窗口。不过在 Terminal-Bench 4.0 上，Opus 5 的 51.8 仍明显高于 Flash 的 42.3。
DeepSeek V4.1 Flash‑1017 beats GPT‑5.6 Sol and Opus 5 on selected coding and agent benchmarks, at much lower token prices. Super duper impressive!
API pricing per million tokens, uncached input / output:
- DeepSeek Flash‑1017: $0.15 / $0.60 off-peak; $0.30 / $1.20 peak. - GPT‑6 Luna: $0.10 / $0.50. - GPT‑5.6 Sol: $4 / $20. - Claude Opus 5: $5 / $25.
Luna is cheaper per uncached token. Flash is substantially cheaper than Sol and Opus, while beating them on some of DeepSeek’s reported tests.
Key benchmarks: - DeepSWE: 77.0 vs 74.2 for the previous Flash, 73.0 for GPT‑5.6 Sol and 74.0 for Opus 5. - Terminal-Bench 4.0: 42.3 vs 31.2 for the previous Flash, 39.9 for GPT‑5.6 Sol and 51.8 for Opus 5. - Automation-Bench: 60.5 vs 54.8 for the previous Flash, 45.8 for GPT‑5.6 Sol and 50.3 for Opus 5.
DeepSeek also reports faster task completion and shorter outputs. Open weights under MIT, with a 1M-token context window.
So yeah, super impressive price-performance launch!
