Artificial Analysis · Intelligence IndexBenchmarks, as Artificial Analysis ran them- 85%GPQA Diamond
- 21%Humanity's Last Exam
- 35%Terminal-Bench Hard
- 95%τ²-Bench
- 72%IFBench
- 73%Long context reasoning
- Per 1M tokens
- $0.30 in · $1.20 out
- Context
- 205K tokens
LMArena · Text176thof 416· 64th of 226 open models
Rated by versionMiniMaxRated 47 points above MiniMax M2; MiniMax M3 rates 51 points higher.
MiniMax M2.5 · 1,391 (1,387–1,395) · 176th
Against list priceRating for the price
MiniMax M2.5 · 1,391 · $0.44 per 1M tokens ($0.27 in, $0.95 out) · 205K context
MiniMax M2.5 · 1,391 · $0.44 per 1M tokens ($0.27 in, $0.95 out) · 205K context
LMArena, CC BY 4.0, 15 October 2026 · prices OpenRouter, list price blended 3:1, read 21 October 2026 · Artificial Analysis, read 21 October 2026