NOUMENOpen app
NOUMEN

inclusionai · Efficient

Ling 3.0 Flash Thinking

Added Jul 23, 2026

Compare models

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

Loading models…

Use in the app

Ling-3.0-flash Thinking enables visible reasoning on inclusionAI's token-efficient 124B-parameter Mixture-of-Experts model for harder coding, tool use, planning, and production-scale agent workflows.

  • Reasoning
  • Tools
Input
Text
Output
Text
Reasoning effort
none · minimal · low · medium · high · xhigh
Discovery tier
Efficient

Pricing

USD per 1M tokens
Input
$0.075
Output
$0.22
Cache read
$0.015

Reference prices as published by the model provider. API example

Specifications

Context window
262.1K
Max output
32.8K
Average output (7 days)
243 tokens
Longer than 25% of 468 models

Side by side

Ling 3.0 Flash Thinking 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…

Ling 3.0 Flash ThinkinginclusionaiThis modelMiniMax M2.1MiniMaxRemove
ProviderinclusionaiMiniMax
Discovery tierEfficientOpen weights
AddedJul 23, 2026Jan 20, 2025
Limits
Context window262.14KBest200K
Max output32.77K131.07KBest
Average output243 tokens359 tokens
Pricing, USD per 1M tokens
Input$0.075Best$0.30
Output$0.22Best$1.20
Cache read$0.015Best$0.03
Performance
Request success (24h)100.0%—
Benchmark indexes
Intelligence Index20.120.9Best
Coding Index50.6—
Math Index—82.7
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputNoYes
Reasoning effortnone, minimal, low, medium, high, xhigh—

Public evaluations

Benchmarks

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

  • Ling 3.0 Flash Thinking
  • MiniMax M2.1

Intelligence Index

  • Ling 3.0 Flash Thinking20.1
  • MiniMax M2.120.9

Ling 3.0 Flash Thinking: Better than 49% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Ling 3.0 Flash Thinking: 50.6
    • MiniMax M2.1: —

  • Math Index

    Composite of the math evaluations

    • Ling 3.0 Flash Thinking: —
    • MiniMax M2.1: 82.7

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Ling 3.0 Flash Thinking: 3.2%
    • MiniMax M2.1: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Ling 3.0 Flash Thinking: 0.6%
    • MiniMax M2.1: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Ling 3.0 Flash Thinking: 798 Elo
    • MiniMax M2.1: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Ling 3.0 Flash Thinking: 948 Elo
    • MiniMax M2.1: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Ling 3.0 Flash Thinking: 5.4%
    • MiniMax M2.1: —

  • AA-LCRv1.1

    Reasoning across long documents

    • Ling 3.0 Flash Thinking: 73.0%Top
    • MiniMax M2.1: 67.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • Ling 3.0 Flash Thinking: 5.0%
    • MiniMax M2.1: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Ling 3.0 Flash Thinking: 23.7%Top
    • MiniMax M2.1: 23.2%

  • GPQA Diamond

    Graduate-level science questions

    • Ling 3.0 Flash Thinking: 85.5%Top
    • MiniMax M2.1: 83.0%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Ling 3.0 Flash Thinking: —
    • MiniMax M2.1: 87.5%

  • IFBench

    Following precise output instructions

    • Ling 3.0 Flash Thinking: —
    • MiniMax M2.1: 69.9%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Ling 3.0 Flash Thinking: 0.0%
    • MiniMax M2.1: —

  • SciCode

    Scientific computing in Python

    • Ling 3.0 Flash Thinking: 42.0%
    • MiniMax M2.1: —

  • LiveCodeBench

    Recent competitive programming problems

    • Ling 3.0 Flash Thinking: —
    • MiniMax M2.1: 81.0%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • Ling 3.0 Flash Thinking: —
    • MiniMax M2.1: 82.7%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Ling 3.0 Flash Thinking: —
    • MiniMax M2.1: 28.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Ling 3.0 Flash Thinking: —
    • MiniMax M2.1: 85.4%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Ling 3.0 Flash Thinking: 73.0%Top
    • MiniMax M2.1: 67.7%

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.

Request success (24h)
100.0%
Reliable
Hourly request success · last 72 hoursLowest hour 100.0%
  • 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": "inclusionai/ling-3.0-flash:thinking",
    "reasoning_effort": "medium",
    "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="inclusionai/ling-3.0-flash:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

inclusionai

Other inclusionai models, starting with the same family.