MiniMax M2.7

Released

Mar 18, 2026

Price in / out

—

Blended $/1M

—

Context

200K

Parameters: 230B / 10B active. License: Modified MIT.

Benchmark scoresvs MiniMax M2.5

Benchmark	Score	Δ vs prior	Rank (current)	Configuration	Source
Terminal-Bench 2.1	48.7%	—	#20 of 21	leaderboard	benchlm.ai ↗
GPQA Diamond	87%	—	#9 of 11	leaderboard	benchlm.ai ↗
AIME 2026	89.8%	—	#2 of 2	leaderboard	benchlm.ai ↗
τ²-bench (Telecom)	84.8%	-10.5	#6 of 10	leaderboard	benchlm.ai ↗
Artificial Analysis Intelligence Index	38.1	+4.5	#6 of 11	leaderboard	benchlm.ai ↗

MiniMax versions

Timeline

Version	Released	$ in / out	Terminal-Bench	SWE-bench	GPQA	AIME	τ²-bench	AA Index
MiniMax M2.5Superseded	2026-02-12	—	—	—	—	—	95.3%	33.6
MiniMax M2.7Superseded	2026-03-18	—	48.7%	—	87%	89.8%	84.8%	38.1
MiniMax M3	2026-06-01	$0.3 / $1.2	53.6%	80.5%	—	—	88.9%	44.4

Compare

Open the Comparison Lab with MiniMax M2.7 and its open-weight peers pre-selected, then toggle any benchmark or model.

Every MiniMax version over time

Shipping with it?

Benchmarks are a starting point. If you run MiniMax M2.7 in production, post what it does well and where it falls over; other founders are deciding right now.

Write about MiniMax M2.7

Current open-weight peers

All

gpt-oss-120bOpenAI Gemma 4 31BGoogle DeepMind Muse Glimmer 30BMeta DeepSeek V4.1 Flash$0.14 in DeepSeek V4 Pro$0.435 in Kimi K3$3 in