The best MiniMax model for reasoning is MiniMax M3 — 54.7 intelligence with extended step-by-step thinking. MiniMax M2.7 (49.6) and MiniMax M2.5 (41.9) round out the top three.
Large language models with extended reasoning / thinking, ranked by intelligence. The best models for complex multi-step reasoning, math and analysis.
The best MiniMax model for reasoning is MiniMax M3 — 54.7 intelligence with extended step-by-step thinking. MiniMax M2.7 (49.6) and MiniMax M2.5 (41.9) round out the top three.
MiniMax M2.7 (49.6) is the closest alternative on this metric, followed by MiniMax M2.5 (41.9). See the full ranking above for the tradeoffs.
modelgrep tracks 8 MiniMax models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by MiniMax M3. 6 of them qualify for this ranking.