Artificial Analysis
#27of 51
Score 22.8. Best run: minimax/minimax-m2.7.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
Minimax
MiniMax M2.7 benchmarks, ranks and price
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place MiniMax M2.7, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Oct 1, 2026
#45of 85
on the LLM leaderboard, with a consensus score of 47 across 2 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Where each leaderboard places MiniMax M2.7
LiveBench
Not measured by LiveBench.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#45of 79
Score 1417. Best run: minimax-m2.7.
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
$0.37
OpenRouter: $0.21 in, $0.84 out. Vercel AI Gateway: $0.30 in, $1.20 out Context window 205K tokens.
Nearby
The models either side of MiniMax M2.7
- #42DeepSeek V4 Flash 042349
- #43MiniMax M348
- #44o4-mini-2025-04-1648
- #45MiniMax M2.747
- #46GPT-5 Mini46
- #47Gemini 3.1 Flash Lite Preview45
- #48GPT-5.4 Mini45
Questions about MiniMax M2.7
How good is MiniMax M2.7?
MiniMax M2.7 ranks #45 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 47 out of 100 across 2 leaderboards.
Is MiniMax M2.7 better than o4-mini-2025-04-16?
Not on the consensus: o4-mini-2025-04-16 scores 48 to MiniMax M2.7's 47. Compare them source by source below, since the leaderboards test different things.
Is MiniMax M2.7 better than GPT-5 Mini?
On the consensus, yes: 47 to 46.
How much does MiniMax M2.7 cost?
$0.21 per million input tokens and $0.84 per million output tokens on OpenRouter, the cheaper listing we read. Blended at three input tokens to one output, that is $0.37 per million.
Is MiniMax M2.7 good for coding?
It scores 52.6 on the Artificial Analysis Coding Index, placing it #27 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.