MiniMax-M3.1-Flash scores 42 on Artificial Analysis Intelligence Index at lower task cost

What happened

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.

The story so far

MiniMax released MiniMax-M3.1-Flash through its API, and Artificial Analysis reported that the model scored 42 on its Intelligence Index at maximum effort, up from MiniMax-M3’s 29, while costing less than half as much per Index task. Artificial Analysis estimated task costs at approximately $0.22 versus $0.51 for M3. The score tied GLM-5.3-Flash and trailed DeepSeek V4.1 Flash 1017, which scored 45. The model supports text and image inputs with up to one million tokens of context. API pricing is $0.15 per million input tokens and $0.60 per million output tokens. Its weights are currently closed; MiniMax plans to release open weights on October 23. Artificial Analysis also found a weakness in its AA-Omniscience evaluation: MiniMax-M3.1-Flash answered 56% of questions correctly but attempted almost every question, producing a reported hallucination rate of 93% and an overall score of 16.

Keep reading