Compare / MiniMax M2 vs Nemotron 3 Nano 30B A3B

MiniMax M2 vs Nemotron 3 Nano 30B A3B

Which is cheaper, which is more capable, and which does better at each kind of work, from 17 results on 3 sources that measured both models.

MiniMax M2
MiniMax · profile
Nemotron 3 Nano 30B A3B
NVIDIA · profile
Results compared
17
Shared sources
3

MiniMax M2 or Nemotron 3 Nano 30B A3B? The short answer

  • Nemotron 3 Nano 30B A3B is cheaper: $0.088 against $0.52 per million tokens, 6.0 times less.
  • MiniMax M2 scores higher on the Artificial Analysis Intelligence Index: 18.6 against 8.9.
  • On our business benchmarks, MiniMax M2 ranks higher for reasoning and knowledge and writing.
  • On our business benchmarks, Nemotron 3 Nano 30B A3B ranks higher for agents and tool use and sticking to the facts.

At a glance

MiniMax M2Nemotron 3 Nano 30B A3B
Price per million tokens$0.30 in · $1.20 out$0.050 in · $0.20 out
Blended (3 in : 1 out)$0.52$0.088
Cheapest host, blended$0.45 (Minimax, FP8)$0.088 (Crusoe, FP8)
Intelligence Index18.68.9
Spring Prompt overall––
Output speed, tokens a second–220
Context window204,800 tokens262,144 tokens
WeightsOpenOpen
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 M2Nemotron 3 Nano 30B A3B
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 149 of 161 145 of 161
Reasoning and knowledgeHard questions across science, maths and general knowledge 107 of 195 130 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 167 of 187 169 of 187
Sticking to the factsSummarising without inventing things, and factual answers 150 of 153 121 of 153

Every shared result

BenchmarkMetricMiniMax M2Nemotron 3 Nano 30B A3B
Arena (formerly LMArena)reportedOverallArena rating 1,3601,362
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3481,317
Arena (formerly LMArena)reportedCreative writingArena rating 1,2851,241
Arena (formerly LMArena)reportedExpert promptsArena rating 1,3501,331
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3341,291
Arena (formerly LMArena)reportedOverallArena rating 1,3431,313
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,2981,267
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 18.68.90
Artificial AnalysisreportedGPQA Diamond% of questions 77.7%75.7%
Artificial AnalysisreportedHumanity's Last Exam% of questions 13.7%11.4%
Artificial AnalysisreportedIFBench% of instructions 72.3%71.1%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 64.3%38.0%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 25.8%13.6%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 86.8%40.9%
UGI LeaderboardreportedRequested-length error% off the requested word count 73.0%35.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.360.28
UGI LeaderboardreportedWriting scorescore out of 100 17.225.9

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 Nemotron 3 Nano 30B A3B?

It depends on the task. Among models available today, on our benchmarks and licensed sources, MiniMax M2 ranks higher for reasoning and knowledge and writing; Nemotron 3 Nano 30B A3B ranks higher for agents and tool use and sticking to the facts.

Which is cheaper, MiniMax M2 or Nemotron 3 Nano 30B A3B?

Nemotron 3 Nano 30B A3B costs $0.088 per million tokens (three input to one output), against $0.52 for MiniMax M2.

Run MiniMax M2 and Nemotron 3 Nano 30B A3B on your own prompt

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