deepseek-v4.1POST

Predicting DeepSeek-V4.1-Flash-1017 lands around 45–48 on Intelligence Index

The author estimates DeepSeek-V4.1-Flash-1017 will score 45–48 on the Intelligence Index, citing models currently at 44–46 such as Grok 4.7, GPT-6 Astra, Qwen3.8-Max, GLM-5.3 and Kimi K3 as reference points.

Leo · Building w/ AI

@leo114119Archived 12 days agoOriginally posted 2026.10.18

Leo · Building w/ AI @leo114119Originally posted 2026.10.18

Open original on X

DeepSeek-V4.1-Flash-1017预测Intelligence Index 分数为 45 或 46，甚至还能再高一点到 47 或者 48？这是一个相对合理的分数：目前处在 46 的模型是 xhigh 和 high 档的 Grok 4.7、低 effort 档的 MiMo-V2.6-Pro 和 GPT-6 Astra。处在 45 的是 Qwen3.8-Max（0902）、xhigh 档的 Muse Spark 1.3 和 max 档的 GLM-5.3。处在 44 的是 Step 5 Preview 和 max 档的 Kimi K3 https://www.orcarouter.ai/zh-CN/blog/deepseek-v4-1-flash-1017-artificial-analysis-rank#where-45-46-comes-from-and-why-you-cannot-check-it

x.com/leo114119/status/2111655767011098852Archived 2026.10.18 16:25