Artificial Analysis · Intelligence Index Benchmarks, as Artificial Analysis ran them 78% GPQA Diamond 14% Humanity's Last Exam 26% Terminal-Bench Hard 83% LiveCodeBench 78% AIME 2025 87% τ²-Bench 82% MMLU-Pro 72% IFBench 64% Long context reasoning
Per 1M tokens $0.30 in · $1.20 out
Context 205K tokens Text WebDev
Overall 227th Multi-turn 202nd Polish 206th Math 212th Hard prompts 218th Instruction following 222nd Expert 222nd Coding 233rd Longer queries 237th Creative writing 261st
LMArena · Text 227th of 416 · 89th of 226 open models
Rated by version MiniMax MiniMax M3 rates 98 points higher.
M2 #227 M2.5 #176 M2.7 #140 M3 #96 MiniMax M2 · 1,343 (1,336–1,351) · 227th
Against list price Rating for the price
1340 1360 1380 1400 1420 1440 1460 1480 1500 1520 $0.03 $0.1 $0.3 $1 $3 $10 $30 MiniMax M2 Muse Wonder Gemini 3.8 Flash Gemini 3.7 Flash GLM-5.3 DeepSeek V4.1 Flash MiniMax M2 · 1,343 · $0.45 per 1M tokens ($0.26 in, $1.02 out) · 205K context
1340 1360 1380 1400 1420 1440 1460 1480 1500 1520 $0.03 $0.1 $0.3 $1 $3 $10 $30 MiniMax M2 Muse Wonder Gemini 3.8 Flash Gemini 3.7 Flash GLM-5.3 DeepSeek V4.1 Flash MiniMax M2 · 1,343 · $0.45 per 1M tokens ($0.26 in, $1.02 out) · 205K context
LMArena , CC BY 4.0, 15 October 2026 · prices OpenRouter , list price blended 3:1, read 20 October 2026 · Artificial Analysis , read 20 October 2026
MiniMax M2