Skip to content
K = 0.731

Artificial Analysis Finds MiniMax-M3.1-Flash Improves Intelligence Score and Lowers Task Cost

1 reports 1 reporting sources 3 hours agoNew

Understand the event

AI overview

Artificial Analysis benchmarked MiniMax-M3.1-Flash at its maximum effort setting and reported an Intelligence Index score of 42, 13 points above MiniMax-M3, at a lower cost per Index task. The score tied GLM-5.3-Flash but trailed DeepSeek V4.1 Flash 1017, which scored 45. Artificial Analysis put the cost per Index task at approximately $0.22, compared with approximately $0.51 for MiniMax-M3. The model’s AA-Omniscience results showed a separate weakness: Artificial Analysis reported that it answered 56% of questions correctly but attempted almost every question, yielding a 93% hallucination rate and an overall score of 16. MiniMax-M3.1-Flash is currently available through MiniMax’s first-party API with closed weights; MiniMax has announced an open-weights release for October 23.

Generated by AI from reports · Updated 2 hours ago

Latest development10/19 23:58 (UTC+8)
MiniMax-M3.1-Flash scores 42 on Artificial Analysis Intelligence Index at lower task costArtificial Analysis · X

Models in this story

API prices of all models

Report timeline

Follow the reports to explore different sides of the event.

10/19
  1. Artificial Analysis · X
    MiniMax-M3.1-Flash scores 42 on Artificial Analysis Intelligence Index at lower task cost

    Artificial Analysis benchmarked MiniMax-M3.1-Flash at max effort, reporting an Intelligence Index score of 42, up 13 points from MiniMax-M3 and level with GLM-5.3-Flash, but behind DeepSeek V4.1 Flash 1017 at 45. Its cost per Index task was ~$0.22 versus MiniMax-M3's ~$0.51, using ~189M output tokens. On AA-Omniscience, it answered 56% correctly but attempted almost every question, yielding a 93% hallucination rate and an overall score of 16.

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