NOUMENOpen app
NOUMEN

MiniMax · Balanced

MiniMax M2-her

Added Jan 12, 2025

Compare models

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

Loading models…

Use in the app

Dialogue-focused MiniMax model optimized for role-playing and multi-turn conversations with rich role settings.

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$0.30
Output
$1.21

Reference prices as published by the model provider. API example

Specifications

Context window
65.5K
Max output
2K
Average output (7 days)
186 tokens
Longer than 20% of 468 models

Side by side

MiniMax M2-her 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-herMiniMaxThis modelMiniMax M3 ThinkingMiniMaxRemove
ProviderMiniMaxMiniMax
Discovery tierBalancedOpen weights
AddedJan 12, 2025Jun 1, 2026
Limits
Context window65.53K512KBest
Max output2.05K80KBest
Average output186 tokens1.9K tokens
Pricing, USD per 1M tokens
Input$0.30$0.23Best
Output$1.21$0.96Best
Cache read—$0.05
Performance
Throughput—185.0 tok/s
Time to first token—7.3 s
Request success (24h)—99.9%
Benchmark indexes
Intelligence Index—29.2
Coding Index—58.6
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • MiniMax M2-her
  • MiniMax M3 Thinking

Intelligence Index

  • MiniMax M2-her—
  • MiniMax M3 Thinking29.2
3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 58.6

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 21.3%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 4.4%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 1,089 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 1,243 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 9.8%

  • AA-LCRv1.1

    Reasoning across long documents

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 83.0%

  • MLCR-AA

    Long-context reasoning over medical records

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 4.4%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 39.0%

  • GPQA Diamond

    Graduate-level science questions

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 92.9%

  • IFBench

    Following precise output instructions

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 82.9%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 2.0%

  • SciCode

    Scientific computing in Python

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 47.1%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 42.4%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 88.9%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • MiniMax M2-her: —
    • MiniMax M3 Thinking: 83.0%

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

MiniMax

Other MiniMax models, starting with the same family.