Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models741Deals30d271Policy30d66, 14 pendingSources1,015

MiniMax M2

MiniMaxReleased Oct 26, 2025Current

Score basis

MiniMax M2 is behind the leaders in instruction following, long context, reasoning, agentic tasks, and coding. Too few results yet to rate safety, math, multimodal tasks, multilingual tasks, or factuality.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Limited5 capabilities
  1. Instruction Following−26.8%1 of 3
  2. Long Context−29.5%1 of 3
  3. Reasoning−38.5%3 of 6
  4. Agentic−40.2%2 of 7
  5. Coding−40.8%5 of 10
Not rated5 capabilities

Too few results yet to rate Safety, Math, Multimodal, Multilingual or Factuality.

Price

$0.30input$1.20outputper million tokens

From Artificial Analysis · 3 providers tracked · All prices

Cheaper than 59% of 330 priced models · 3:1 input-to-output blend, log scale

Evidence

57results on46benchmarks

  • 4 independently verified
  • 15 aggregator
  • 35 vendor-reported
  • 3 cross-referenced

From 8 sources · latest Oct 8, 2026 · How verification works

API features

Tool callingStructured outputsReasoning

As listed by OpenRouter

Research

24 papers reference MiniMax M2

MiniMax M2 benchmark results

57 results on 46 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Instruction Following

LimitedFull instruction following ranking

26.8% behind the leader1 of 3 ranked benchmarks measured

Show 1 more instruction following resultHide 1 instruction following result

Long Context

LimitedFull long context ranking

29.5% behind the leader1 of 3 ranked benchmarks measured

Reasoning

LimitedFull reasoning ranking

38.5% behind the leader3 of 6 ranked benchmarks measured

Show 3 more reasoning resultsHide 3 reasoning results

Agentic

LimitedFull agentic ranking

40.2% behind the leader2 of 7 ranked benchmarks measured

Coding

LimitedFull coding ranking

40.8% behind the leader5 of 10 ranked benchmarks measured

Show 7 more coding resultsHide 7 coding results

Factuality

Not enough dataFull factuality ranking

0 of 4 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

Show 26 more resultsHide 26 results

MiniMax M2: common questions

Who makes MiniMax M2?

MiniMax M2 is made by MiniMax.

When was MiniMax M2 released?

MiniMax M2 was released on Oct 26, 2025, according to Artificial Analysis.

What is MiniMax M2 good at?

MiniMax M2 is behind the leaders in instruction following, long context, reasoning, agentic tasks, and coding. Too few results yet to rate safety, math, multimodal tasks, multilingual tasks, or factuality.

How much does MiniMax M2 cost?

MiniMax M2 costs $0.30 per million input tokens and $1.20 per million output tokens, according to Artificial Analysis. We track its price at 3 providers. At a mix of three input tokens to one output token, it is cheaper than 59% of the 330 priced models we track.

How many benchmarks has MiniMax M2 been tested on?

We track 57 results for MiniMax M2 on 46 benchmarks from 8 sources, 4 of them independently verified. The latest was recorded on Oct 8, 2026.

Which API features does MiniMax M2 support?

OpenRouter lists tool calling, structured outputs, and reasoning for MiniMax M2.

About this record

Where MiniMax M2's numbers come from, and every name it appears under.

Tracked since
Apr 27, 2026
Newest source mention
May 1, 2026

Where the results come from

Verification: 57 scores · 4 independently verified · 15 aggregator-attributed · 3 vendor cross-reference · 35 vendor-reported. How these tiers are assigned

From 8 sources on 6 sites. Hugging Face supplies 26 of them; the 4 independently verified results come from 3 sites. Bars are coloured by trust tier.

  • huggingface.co26
  • artificialanalysis.ai15
  • api.llm-stats.com12
  • swebench.com2
  • datasets-server.huggingface.co1
  • simple-bench.com1