Models Index Compare Best for Benchmarks Status Pricing API

MiniMax M1

MiniMax·Operational·Released 2025-06-16text

Context1,000k

Max output-

Input / 1M-

Output / 1M-

Cached in-

Benchmarks16

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

#125/1411363.9 ↗

#2/986% ↗

#16/2476.9% ↗

FullStackBench

68.3% ↗

#65/8370% ↗

8.4% ↗

LiveCodeBench (24/8~25/5)

65% ↗

LongBench-v2

61.5% ↗

MATH-500

#1/396.8% ↗

#28/4981.1% ↗

OpenAI-MRCR (128k)

73.4% ↗

SimpleQA

#7/718.5% ↗

SWE-bench Verified

#52/5956% ↗

TAU-bench (airline)

62% ↗

TAU-bench (retail)

63.5% ↗

ZebraLogic

#4/686.8% ↗

Compare

vs Gemini 4 Argon vs GPT-6.1 Sol vs Claude Sonnet 5.5 vs Muse Spark 1.3 vs GPT-6 Sol vs GPT-6 Luna vs Claude Opus 5.5 vs GPT-6 Astra

More from MiniMax

MiniMax M3 MiniMax M2.7 MiniMax M2.5 MiniMax M2 MiniMax M2.1 MiniMax M3.1 Flash Preview

MiniMax M1 FAQ

What is MiniMax M1?: MiniMax M1 is a large language model from MiniMax, released on June 16, 2025. It accepts text input.
When was MiniMax M1 released?: MiniMax released MiniMax M1 on June 16, 2025.
What is MiniMax M1's context window?: MiniMax M1 has a 1M-token context window.
How does MiniMax M1 score on benchmarks?: MiniMax M1 has 16 cited benchmark scores, including LMArena Elo 1363.9 Elo, AIME 2024 86% and AIME 2025 76.9%. Each score links to its source.

Access MiniMax M1 and every other model through one endpoint with automatic failover: Respan gateway.