Benchmarks

MiniMax pitches M3 as a coding contender, but the key benchmark claim remains thinly sourced

MiniMax pitches M3 as a coding contender, but the key benchmark claim remains thinly sourced

MiniMax is being cited in wire coverage as claiming a 59% score on SWE-bench for its new M3 model, with reports framing that result as ahead of GPT-5.5. Based on the available evidence, the central performance figure is vendor-reported and the underlying test conditions are not disclosed. That makes the announcement notable for competitive positioning in coding models, but still hard for builders and enterprise buyers to verify.

Featured

Benchmarks

Latest News and Analysis in Benchmarks