Skip to content
aiqbench

MiniMax · model passport

MiniMax: MiniMax M2.1

minimax-m2-1
  • Open weights
  • 228.7B params
  • 204,800 context
  • Released 2025-12-20(HF repo created)
4/27axes covered
Best percentile
98.5MMLU-Pro (Artificial Analysis)
Cohort standing
66.4median 54.9

What the data says

Benchmarked on 4 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 98.5 pct — MMLU-Pro (Artificial Analysis) (87.5%)
  • 91.6 pct — LiveCodeBench (Artificial Analysis) (81.0%)

Uneven: 55.3 percentile points between its best and worst axis — 98.5 pct on MMLU-Pro (Artificial Analysis) versus 43.2 pct on Terminal-Bench.

  • MMLU-Pro (Artificial Analysis)98.5 pct87.5%Verify →
  • LiveCodeBench (Artificial Analysis)91.6 pct81.0%Verify →
  • IFBench (Artificial Analysis)81.5 pct69.9%Verify →
  • Terminal-Bench43.2 pct36.6%Verify →
  • OverallNot benchmarked
  • WebDev ArenaNot benchmarked
  • Vision ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot benchmarked
  • CodingNot benchmarked
  • Instruction followingNot benchmarked
  • Hard promptsNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Run it yourself

RepositoryMiniMaxAI/MiniMax-M2.1
Parameters228.7B
ArchitectureMiniMaxM2ForCausalLM

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "MiniMaxAI/MiniMax-M2.1"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

Ollama

We don't sync Ollama tags, so we won't print a command we can't verify — a wrong one would pull the wrong model. Search the Ollama library →

Unsloth fine-tuning recipes are model-specific and we don't derive them here. Unsloth docs →

Use it hosted

API model IDminimax/minimax-m2.1
Context length204,800 tokens
Max output131,072 tokens
Input price$0.30 per 1M tokens
Cached input price$0.03 per 1M tokens
Output price$1.20 per 1M tokens

API parameters this endpoint supports

Include reasoningMax tokensReasoningResponse formatTemperatureTool choiceTool callingTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"minimax/minimax-m2.1","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • MiniMax-M2.1 stands at 66.4 (raw mean 78.7) — measured on 4 of 27 axes.

    standingtemplateVerify →

  • MiniMax-M2.1 stands at 66.4 versus a cohort median of 54.9 across 126 models released within 180 days — above the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →