Skip to content

DeepSeek V4.1 Flash 1017 Ties for Second Among Open-Weight Models in Artificial Analysis Ranking

1 reports 1 reporting sources 2 hours agoNew

Understand the event

AI overview

Artificial Analysis evaluated DeepSeek V4.1 Flash 1017 and gave it an Intelligence Index score of 45, up 6 points from DeepSeek V4.1 Flash and tied with GLM-5.3 for second among open-weight models. The evaluator reported gains in agentic capabilities, knowledge, and scientific reasoning. Artificial Analysis measured its Cost per Task at $0.26, compared with $0.13 for MiMo-V2.6-Pro and $0.21 for GPT-6.1 Sol (medium), both of which scored higher on the index.

Generated by AI from reports · Updated 2 hours ago

Models in this story

  • DeepSeek V4.1 Flash#28 overall$0.032 input / $0.08 output per million tokens
  • GLM-5.3#15 overall$0.079 input / $1.4 output per million tokens
  • MiMo V 2.6 Pro#13 overall$0.43 input / $0.87 output per million tokens
  • GPT-6.1 Sol#6 overall$2 input / $10 output per million tokens

Report timeline

Follow the reports to explore different sides of the event.

10/20
  1. DeepSeek V4.1 Flash 1017 scores 45 on Artificial Analysis Intelligence Index

    Artificial Analysis reports that DeepSeek V4.1 Flash 1017 scores 45 on its Intelligence Index, improving by 6 points over DeepSeek V4.1 Flash and tying GLM-5.3 for #2 among open-weights models. Its evaluation finds gains in agentic capabilities, knowledge, and scientific reasoning. Cost per Task is $0.26, compared with $0.13 for MiMo-V2.6-Pro and $0.21 for GPT-6.1 Sol (medium), both of which score higher.

Tomorrow at 08:00, a briefing like this arrives in your inbox.

The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue

Event heat trend

There is not enough continuous observation data to plot a trend yet.

Keep reading

Latest daily · Issue 26VAST open-sources EdenLive world model with over 24FPS generation at 720P