NOUMENOpen app
NOUMEN

MiniMax · Open weights

MiniMax M2.7

Added Mar 18, 2026Open weights

Compare models

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

Loading models…

Use in the app

MiniMax M2.7 is the first model deeply involved in iterating on its own training. It excels in real-world software engineering (SWE-Pro 56.22%), end-to-end project delivery (VIBE-Pro 55.6%), and complex office workflows with strong tool-use compliance and agentic capabilities.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.21
Output
$0.84
Cache read
$0.042

Reference prices as published by the model provider. API example

Specifications

Context window
204.8K
Max output
131.1K
Average output (7 days)
556 tokens
Longer than 52% of 465 models

Side by side

MiniMax M2.7 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 M2.7MiniMaxThis modelQwen3.5 27B TEEQwenRemove
ProviderMiniMaxQwen
Discovery tierOpen weightsOpen weights
AddedMar 18, 2026Mar 13, 2026
Limits
Context window204.8K262.14KBest
Max output131.07KBest65.54K
Average output556 tokens1.4K tokens
Pricing, USD per 1M tokens
Input$0.21Best$0.30
Output$0.84Best$2.40
Cache read$0.042—
Performance
Throughput24.3 tok/s—
Time to first token0.9 s—
Request success (24h)100.0%—
Benchmark indexes
Intelligence Index22.822.9Best
Coding Index52.6—
Capabilities
ReasoningYesNo
ToolsYesNo
VisionNoYes
Structured outputYesNo
Video inputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • MiniMax M2.7
  • Qwen3.5 27B TEE

Intelligence Index

  • MiniMax M2.722.8
  • Qwen3.5 27B TEE22.9

MiniMax M2.7: Better than 55% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • MiniMax M2.7: 52.6
    • Qwen3.5 27B TEE: —

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • MiniMax M2.7: 4.4%
    • Qwen3.5 27B TEE: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • MiniMax M2.7: 0.3%
    • Qwen3.5 27B TEE: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • MiniMax M2.7: 718 Elo
    • Qwen3.5 27B TEE: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • MiniMax M2.7: 1,008 Elo
    • Qwen3.5 27B TEE: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • MiniMax M2.7: 6.0%
    • Qwen3.5 27B TEE: —

  • AA-LCRv1.1

    Reasoning across long documents

    • MiniMax M2.7: 78.3%Top
    • Qwen3.5 27B TEE: 77.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • MiniMax M2.7: 5.6%
    • Qwen3.5 27B TEE: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • MiniMax M2.7: 29.6%Top
    • Qwen3.5 27B TEE: 23.9%

  • GPQA Diamond

    Graduate-level science questions

    • MiniMax M2.7: 87.4%Top
    • Qwen3.5 27B TEE: 85.8%

  • IFBench

    Following precise output instructions

    • MiniMax M2.7: 75.7%Top
    • Qwen3.5 27B TEE: 75.6%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • MiniMax M2.7: 0.0%
    • Qwen3.5 27B TEE: —

  • SciCode

    Scientific computing in Python

    • MiniMax M2.7: 50.1%
    • Qwen3.5 27B TEE: —

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • MiniMax M2.7: 39.4%Top
    • Qwen3.5 27B TEE: 32.6%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • MiniMax M2.7: 84.8%
    • Qwen3.5 27B TEE: 93.9%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • MiniMax M2.7: 78.3%Top
    • Qwen3.5 27B TEE: 77.7%

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

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput
24.3 tok/s
Faster than 15% of 251 models
Time to first token
0.9 s
Quicker than 97% of 251 models
Prompt cache hits
46.2%
About $0.13 per 1M input tokens with caching
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 70.5%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

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": "minimax/minimax-m2.7",
    "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="minimax/minimax-m2.7",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

MiniMax

Other MiniMax models, starting with the same family.