Compare / MiniMax M2 vs o1

MiniMax M2 vs o1

Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 3 sources that measured both models.

MiniMax M2
MiniMax · profile
o1
OpenAI · profile
Results compared
16
Shared sources
3

MiniMax M2 or o1? The short answer

  • MiniMax M2 is cheaper: $0.52 against $26.25 per million tokens, 50 times less.
  • MiniMax M2 scores higher on the Artificial Analysis Intelligence Index: 18.6 against 15.2.
  • On our business benchmarks, MiniMax M2 ranks higher for reasoning and knowledge.
  • On our business benchmarks, o1 ranks higher for writing and sticking to the facts.

At a glance

MiniMax M2o1
Price per million tokens$0.30 in · $1.20 out$15.00 in · $60.00 out
Blended (3 in : 1 out)$0.52$26.25
Cheapest host, blended$0.45 (Minimax, FP8)–
Intelligence Index18.615.2
Spring Prompt overall––
Output speed, tokens a second––
Context window204,800 tokens200,000 tokens
WeightsOpenClosed
Developer based inChinathe US

Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.

Which is better for what

Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.

Use caseMiniMax M2o1
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 149 of 161 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 107 of 195 126 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 167 of 187 74 of 187
Sticking to the factsSummarising without inventing things, and factual answers 150 of 153 86 of 153

Every shared result

BenchmarkMetricMiniMax M2o1
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3481,370
Arena (formerly LMArena)reportedCreative writingArena rating 1,2851,381
Arena (formerly LMArena)reportedExpert promptsArena rating 1,3501,402
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3341,407
Arena (formerly LMArena)reportedOverallArena rating 1,3431,402
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,2981,398
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 18.615.2
Artificial AnalysisreportedGPQA Diamond% of questions 77.7%74.7%
Artificial AnalysisreportedHumanity's Last Exam% of questions 13.7%7.0%
Artificial AnalysisreportedIFBench% of instructions 72.3%70.3%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 64.3%65.0%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 25.8%12.9%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 86.8%62.6%
UGI LeaderboardreportedRequested-length error% off the requested word count 73.0%24.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.360.36
UGI LeaderboardreportedWriting scorescore out of 100 17.261.0

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.

Quick answers

Is MiniMax M2 better than o1?

It depends on the task. Among models available today, on our benchmarks and licensed sources, MiniMax M2 ranks higher for reasoning and knowledge; o1 ranks higher for writing and sticking to the facts.

Which is cheaper, MiniMax M2 or o1?

MiniMax M2 costs $0.52 per million tokens (three input to one output), against $26.25 for o1.

Run MiniMax M2 and o1 on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.