Model

MiniMax M2.7

OPEN

MiniMax · MiniMax M2.7 family · released Mar 18, 2026

Agentic coding/reasoning model billed by MiniMax as its first model to autonomously drive a meaningful share of its own RL research/development workflow ("self-evolution"). Open weights on Hugging Face; also served via a 2x-priced 'M2.7-highspeed' deployment tier (same weights, faster serving) which is not modeled as a separate entry here.

ReasoningCodingVisionFunction callingTool useAgentic

2148.5

Elo · rank #49

Parameters

230B

Active params

10B (MoE)

Context

200K tokens

Architecture

Sparse Mixture-of-Experts, 256 local experts (8 active/token), 62 layers, RoPE + QK-RMSNorm attention; 230B total / 10B active params (~4.3% activation)

License

MiniMax Model Community License (non-commercial use restrictions; commercial use requires separate agreement) — verify exact license text at https://huggingface.co/MiniMaxAI/MiniMax-M2.7/blob/main/LICENSE

Languages

—

API price (in/out)

$0.3 / $1.2

Modalities

text

Benchmark results

Bar shows position within the tracked field; marker = field best

Agents' Last ExamAgents14.2%#20

best: GPT-5.6 · 52.7%

AIMEMath94.2%#21

best: GPT-5.2 · 100.0%

BrowseCompAgents77.8%#17

best: Kimi K3 · 91.2%

GDPval-AAAgents1495#16

best: Claude Fable 5 · 1932

GPQA DiamondReasoning87.0%#46

best: GPT-5.6 · 94.6%

Humanity's Last ExamReasoning28.0%#50

best: Claude Sonnet 5 · 57.4%

IFBenchReasoning76.0%#15

best: MiniMax M3 · 83.0%

MMLU-ProKnowledge81.8%#48

best: Claude Fable 5 · 91.5%

SWE-bench ProCoding56.2%#21

best: Claude Fable 5 · 80.0%

SWE-bench VerifiedCoding75.4%#40

best: Claude Fable 5 · 95.0%

Terminal-Bench 2.0Coding55.0%#41

best: GPT-5.6 · 88.8%

Run it locally

VRAM @ Q4

—

VRAM @ FP16

—

Fits on (Q4)

Multi-node cluster required

Throughput data unavailable.

Quantizations

—

MiniMax M2.7 family

Elo progression across releases

MiniMax M2.7Mar 20262148.5

Resources

HFMiniMaxAI/MiniMax-M2.7 DOCShttps://platform.minimax.io/docs/release-notes/models APIAvailable via MiniMax API

API price $0.3/$1.2 · each benchmark row carries its own source badge (see methodology)