deepseek-v4.1POST
DeepSeek V4.1 Flash in Cursor: 47.7% on CursorBench under $1 per task
DeepSeek V4.1 Flash landed in Cursor, hitting 47.7% on CursorBench at max effort for under a dollar per task versus roughly 57% for Opus 5.5.
BlockedPath
@BlockedPathsArchived 2 days agoOriginally posted 2026.10.27
BlockedPath @BlockedPathsOriginally posted 2026.10.27
deepseek v4.1 flash just landed in cursor. max effort hits 47.7% on cursorbench for under a dollar a task, opus 5.5 tops out around 57%. most tickets aren't 57% tickets. what share of your agent runs actually need the top model?
x.com/blockedpaths/status/2114861673865781557Archived 2026.10.27 12:08