Skip to content
Get my AI grade

Minimax

MiniMax M3 benchmarks, ranks and price

Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place MiniMax M3, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.

Updated Oct 1, 2026Full leaderboardSources and method

Read Oct 1, 2026

#43of 85

on the LLM leaderboard, with a consensus score of 48 across 3 leaderboards.

Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.

By leaderboard

Where each leaderboard places MiniMax M3

Artificial Analysis

#20of 51

Score 29.2. Best run: minimax/minimax-m3.

Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.

LiveBench

#29of 34

Score 67.3. Best run: MiniMax M3.

Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.

LMArena

#29of 79

Score 1444. Best run: minimax-m3.

Blind head-to-head human votes, style controlled.

Berkeley BFCL

Not measured by Berkeley BFCL.

Function calling and tool use, single turn to multi turn and web search.

Price and context

$0.52

OpenRouter: $0.30 in, $1.20 out. Vercel AI Gateway: $0.30 in, $1.20 out Context window 1.0M tokens. LiveBench cost per solved task $0.060.

Nearby

The models either side of MiniMax M3

  1. #40Qwen3.5 397B A17B50
  2. #41Gemini 2.5 Pro50
  3. #42DeepSeek V4 Flash 042349
  4. #43MiniMax M348
  5. #44o4-mini-2025-04-1648
  6. #45MiniMax M2.747
  7. #46GPT-5 Mini46

Questions about MiniMax M3

How good is MiniMax M3?
MiniMax M3 ranks #43 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 48 out of 100 across 3 leaderboards.
Is MiniMax M3 better than DeepSeek V4 Flash 0423?
Not on the consensus: DeepSeek V4 Flash 0423 scores 49 to MiniMax M3's 48. Compare them source by source below, since the leaderboards test different things.
Is MiniMax M3 better than o4-mini-2025-04-16?
On the consensus, yes: 48 to 48.
How much does MiniMax M3 cost?
$0.30 per million input tokens and $1.20 per million output tokens on OpenRouter, the cheaper listing we read. Blended at three input tokens to one output, that is $0.52 per million.
Is MiniMax M3 good for coding?
It scores 58.6 on the Artificial Analysis Coding Index, placing it #21 for coding among the models on this leaderboard.

These models recommend brands. See if they name yours.

Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.

  • Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
  • Who gets namedEvery competitor in the answers, most named first.
  • The pages AI readsThe sources behind each answer.
  • Three fixesWhat to fix first, with a brief for the first article.