deepseek-v4.1POST
DeepSeek V4.1 Flash snapshot scores 128/157 with thinking off, math drops to 12/30
The author ran all 157 tests through a Hermes agent with thinking off: 128 points, one better than September, but math fell to 12 of 30, and only effort none actually disables thinking.
Mike Gannotti 🔳
@MichaelGannottiArchived 10 days agoOriginally posted 2026.10.18
Mike Gannotti 🔳 @MichaelGannottiOriginally posted 2026.10.18
Nemo, one of my Hermes agents, ran the new DeepSeek V4.1 Flash snapshot through all 157 tests with thinking off. It scored 128, one up on September, but math fell to 12 of 30. And only effort none actually turns thinking off. https://x.com/MichaelGannotti/status/2111504107844559243
This post quotes another post: x.com/michaelgannotti/status/2111504107844559243
x.com/michaelgannotti/status/2111504236047654987Archived 2026.10.18 16:30