deepseek-v4.1IMAGE
User questions DeepSWE benchmark validity, adds V4.1 Flash 1017 to chart
The user argues DeepSWE has become a joke of a benchmark and manually inserted V4.1 Flash 1017 results into a CodingFleet blog screenshot.
Darek Gusto
@darekgustoArchived 10 days agoOriginally posted 2026.10.17
Darek Gusto @darekgustoOriginally posted 2026.10.17
When did DeepSWE become such a joke of a benchmark... what did go wrong? (screenshot from CodingFleet blog manipulated by me to add new DeepSeek Flash v4.1 1017)
x.com/darekgusto/status/2111391468468490447Archived 2026.10.18 16:42