Skip to content

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 Nov 15, 2026Full leaderboardSources and method

Read Nov 15, 2026

#39of 69

on the LLM leaderboard, with a consensus score of 47 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

#5of 12

Score 18.9. Best run: minimax/minimax-m3.

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

LiveBench

#28of 32

Score 67.3. Best run: MiniMax M3.

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

LMArena

#26of 66

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. #36Inkling xHigh48
  2. #37o4-mini-2025-04-1648
  3. #38Kimi K2.6 Thinking48
  4. #39MiniMax M347
  5. #40gpt-4.1-mini-2025-04-1445
  6. #41mistral-medium-250844
  7. #42Gemini 3.1 Flash Lite Preview44

Questions about MiniMax M3

How good is MiniMax M3?
MiniMax M3 ranks #39 of 69 models on the Rank.ai LLM leaderboard, with a consensus score of 47 out of 100 across 3 leaderboards.
Is MiniMax M3 better than Kimi K2.6 Thinking?
Not on the consensus: Kimi K2.6 Thinking scores 48 to MiniMax M3's 47. Compare them source by source below, since the leaderboards test different things.
Is MiniMax M3 better than gpt-4.1-mini-2025-04-14?
On the consensus, yes: 47 to 45.
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 #5 for coding among the models on this leaderboard.

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.