New todaydeepseek-v4.1IMAGE

DeepSeek V4.1 Flash scores 32 on new Artificial Analysis index, 26 below Opus 5.5

On the new Artificial Analysis index, DeepSeek V4.1 Flash and GLM-5.3 Max score 32, a full 26 points behind Claude Opus 5.5, while Kimi K3.1 Pro leads Chinese models at 46.

Anika🎀❤️

@loveAIwangArchived 10 hours agoOriginally posted 2026.10.28

DeepSeek V4.1 Flash scores 32 on new Artificial Analysis index, 26 below Opus 5.5

Anika🎀❤️ @loveAIwangOriginally posted 2026.10.28

Open original on X

Top 8 on the new Artificial Analysis index: all American labs. The first Chinese model shows up at #9. Kimi K3.1 Pro, 46. DeepSeek V4.1 Flash and GLM-5.3 Max are both down at 32, a full 26 points under Claude Opus 5.5. I did not expect the gap to look THIS wide 😳 https://x.com/ArtificialAnlys/status/2115265133467635877/photo/1

x.com/loveaiwang/status/2115273639855878471Archived 2026.10.28 12:01