NOUMENOpen app
NOUMEN

MiniMax · Balanced

MiniMax M1 80K

Added Jan 8, 2025

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

MiniMax-M1 with 80K thinking budget. Enhanced version of the hybrid MoE reasoning model with double the thinking capacity. Ideal for extremely complex software engineering, tool use, and long context tasks.

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$0.61
Output
$2.42

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
131.1K

Side by side

MiniMax M1 80K compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

MiniMax M1 80KMiniMaxThis modelMistral Small 4 119B ThinkingMistralRemove
ProviderMiniMaxMistral
Discovery tierBalancedOpen weights
AddedJan 8, 2025Mar 17, 2026
Limits
Context window1MBest262.14K
Max output131.07KBest16.38K
Average output—997 tokens
Pricing, USD per 1M tokens
Input$0.61$0.40Best
Output$2.42$1.40Best
Performance
Request success (24h)—93.9%
Benchmark indexes
Intelligence Index11.7Best11.3
Coding Index—26.6
Math Index61.0—
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Structured outputNoYes
Reasoning effort—none, high

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • MiniMax M1 80K
  • Mistral Small 4 119B Thinking

Intelligence Index

  • MiniMax M1 80K11.7
  • Mistral Small 4 119B Thinking11.3

MiniMax M1 80K: Better than 26% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • MiniMax M1 80K: —
    • Mistral Small 4 119B Thinking: 26.6

  • Math Index

    Composite of the math evaluations

    • MiniMax M1 80K: 61.0
    • Mistral Small 4 119B Thinking: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • MiniMax M1 80K: —
    • Mistral Small 4 119B Thinking: 1.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • MiniMax M1 80K: —
    • Mistral Small 4 119B Thinking: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • MiniMax M1 80K: —
    • Mistral Small 4 119B Thinking: 241 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • MiniMax M1 80K: —
    • Mistral Small 4 119B Thinking: 362 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • MiniMax M1 80K: —
    • Mistral Small 4 119B Thinking: 0.0%

  • AA-LCRv1.1

    Reasoning across long documents

    • MiniMax M1 80K: 57.7%Top
    • Mistral Small 4 119B Thinking: 49.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • MiniMax M1 80K: —
    • Mistral Small 4 119B Thinking: 1.7%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • MiniMax M1 80K: 8.9%
    • Mistral Small 4 119B Thinking: 9.9%Top

  • GPQA Diamond

    Graduate-level science questions

    • MiniMax M1 80K: 69.7%
    • Mistral Small 4 119B Thinking: 76.9%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • MiniMax M1 80K: 81.6%
    • Mistral Small 4 119B Thinking: —

  • IFBench

    Following precise output instructions

    • MiniMax M1 80K: 41.8%
    • Mistral Small 4 119B Thinking: 48.2%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • MiniMax M1 80K: —
    • Mistral Small 4 119B Thinking: 0.0%

  • SciCode

    Scientific computing in Python

    • MiniMax M1 80K: —
    • Mistral Small 4 119B Thinking: 38.8%

  • LiveCodeBench

    Recent competitive programming problems

    • MiniMax M1 80K: 71.1%
    • Mistral Small 4 119B Thinking: —

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • MiniMax M1 80K: 61.0%
    • Mistral Small 4 119B Thinking: —

  • AIME

    Competition mathematics

    • MiniMax M1 80K: 84.7%
    • Mistral Small 4 119B Thinking: —

  • MATH-500

    Competition math problems

    • MiniMax M1 80K: 98.0%
    • Mistral Small 4 119B Thinking: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • MiniMax M1 80K: 3.0%
    • Mistral Small 4 119B Thinking: 17.4%Top

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • MiniMax M1 80K: 34.2%
    • Mistral Small 4 119B Thinking: 41.2%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • MiniMax M1 80K: 57.7%Top
    • Mistral Small 4 119B Thinking: 49.7%

Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMaxAI/MiniMax-M1-80k",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'
import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="MiniMaxAI/MiniMax-M1-80k",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

MiniMax

Other MiniMax models, starting with the same family.