deepseek-v4.1IMAGE
DeepSeek V4.1 Flash 1017 beats Opus 5 on DeepSWE and Automation-Bench at 20x lower cost
The poster says the 552B MoE V4.1-flash-1017 beats Opus 5 on DeepSWE and Automation-Bench while costing $1.20/M output tokens ($0.60 off-peak), over 20x cheaper.
Haider.
@haider1Archived 10 days agoOriginally posted 2026.10.17
Haider. @haider1Originally posted 2026.10.17
what DeepSeek just managed with v4.1-flash-1017 is incredible the 552B MoE model now beats opus 5 on DeepSWE and Automation-Bench while costing just $1.20/M output tokens ($0.60 off-peak) over 20x cheaper than opus 5 i still don't understand how they squeezed this much performance out of the same architecture
This post quotes another post: x.com/deepseek_ai/status/2111375640717033777
x.com/haider1/status/2111386785863671883Archived 2026.10.18 16:44