modelgrep

MiniMax: MiniMax M2.7 vs Qwen: Qwen3.6 Max Preview

MiniMax: MiniMax M2.7 wins on more metrics (5 of 9), but the right pick depends on what you optimize for — see the breakdown below.

MetricMiniMax: MiniMax M2.7Qwen: Qwen3.6 Max Preview
Intelligence Index49.651.8
Coding Index41.944.9
GPQA Diamond87%89%
Design Arena Elo1287
Speed (tokens/sec)24929
Latency457ms2.6s
Input price /M$0.250$1.04
Output price /M$1.00$6.24
Context window205K262K
CapabilitiesReasoningToolsJSONReasoningToolsJSON