NOUMENOpen app
NOUMEN

Inception · Balanced

Mercury 2

Added Jan 1, 2024

Compare models

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

Loading models…

Use in the app

Inception Labs' fastest reasoning model with tool calling and structured outputs support.

  • Reasoning
  • Tools
  • Structured output
Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$0.25
Output
$0.75
Cache read
$0.025

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
50K

Side by side

Mercury 2 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…

Mercury 2InceptionThis modelTrinity Large ThinkingarceeRemove
ProviderInceptionarcee
Discovery tierBalancedOpen weights
AddedJan 1, 2024Apr 1, 2026
Limits
Context window128K262.14KBest
Max output50K80KBest
Average output—327 tokens
Pricing, USD per 1M tokens
Input$0.25$0.25
Output$0.75Best$0.90
Cache read$0.025—
Benchmark indexes
Intelligence Index10.810.8
Coding Index31.1Best25.8
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • Mercury 2
  • Trinity Large Thinking

Intelligence Index

  • Mercury 210.8
  • Trinity Large Thinking10.8

Mercury 2: Better than 23% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • Mercury 2: 31.1Top
    • Trinity Large Thinking: 25.8

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Mercury 2: 1.7%Top
    • Trinity Large Thinking: 1.3%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Mercury 2: 0.3%Top
    • Trinity Large Thinking: 0.2%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Mercury 2: 265 EloTop
    • Trinity Large Thinking: 255 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Mercury 2: 494 EloTop
    • Trinity Large Thinking: 336 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Mercury 2: 3.8%Top
    • Trinity Large Thinking: 1.2%

  • AA-LCRv1.1

    Reasoning across long documents

    • Mercury 2: 43.7%Top
    • Trinity Large Thinking: 38.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Mercury 2: 17.1%Top
    • Trinity Large Thinking: 15.8%

  • GPQA Diamond

    Graduate-level science questions

    • Mercury 2: 77.0%Top
    • Trinity Large Thinking: 75.2%

  • IFBench

    Following precise output instructions

    • Mercury 2: 69.8%Top
    • Trinity Large Thinking: 56.3%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Mercury 2: 0.0%
    • Trinity Large Thinking: 0.5%Top

  • SciCode

    Scientific computing in Python

    • Mercury 2: 37.7%
    • Trinity Large Thinking: 40.6%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • Mercury 2: 26.5%Top
    • Trinity Large Thinking: 22.7%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • Mercury 2: 70.8%
    • Trinity Large Thinking: 90.1%Top

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Mercury 2: 43.7%Top
    • Trinity Large Thinking: 38.0%

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": "mercury-2",
    "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="mercury-2",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Inception

Other Inception models, starting with the same family.