/
Published on 18.03.2026
TLDR: MiniMax-M2.7 scores 86.2% on PinchBench (5th overall, within 1.2 points of Claude Opus 4.6) and 47% on Kilo Bench's 89-task gauntlet. It reads more context than any other model tested, which means it catches things others miss — but sometimes runs out of time doing it. At $0.30/M input and $1.20/M output, it undercuts frontier models significantly.
MiniMax-M2.7 Is Now Available in Kilo. Here's How It Performs.