Inception · Balanced
Mercury 2
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.
| Mercury 2InceptionThis model | Granite 4.2 8BibmRemove | |
|---|---|---|
| Provider | Inception | ibm |
| Discovery tier | Balanced | Open weights |
| Added | Jan 1, 2024 | Aug 31, 2026 |
| Limits | ||
| Context window | 128K | 131.07KBest |
| Max output | 50K | — |
| Average output | — | 2.4K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.25 | $0.10Best |
| Output | $0.75 | $0.15Best |
| Cache read | $0.025Best | $0.05 |
| Performance | ||
| Request success (24h) | — | 100.0% |
| Benchmark indexes | ||
| Intelligence Index | 10.8 | 11.1Best |
| Coding Index | 31.1Best | 22.4 |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Structured output | Yes | Yes |
| Reasoning effort | — | none, low, high |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Mercury 2
- Granite 4.2 8B
Intelligence Index
- Mercury 210.8
- Granite 4.2 8B11.1
Mercury 2: Better than 23% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- Mercury 2: 31.1Top
- Granite 4.2 8B: 22.4
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Mercury 2: 1.7%
- Granite 4.2 8B: 2.1%Top
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Mercury 2: 0.3%Top
- Granite 4.2 8B: 0.3%Top
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Mercury 2: 265 Elo
- Granite 4.2 8B: 310 EloTop
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Mercury 2: 494 EloTop
- Granite 4.2 8B: 491 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Mercury 2: 3.8%Top
- Granite 4.2 8B: 0.6%
AA-LCRv1.1
Reasoning across long documents
- Mercury 2: 43.7%
- Granite 4.2 8B: 45.0%Top
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Mercury 2: 17.1%Top
- Granite 4.2 8B: 9.7%
GPQA Diamond
Graduate-level science questions
- Mercury 2: 77.0%Top
- Granite 4.2 8B: 63.1%
IFBench
Following precise output instructions
- Mercury 2: 69.8%
- Granite 4.2 8B: —
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Mercury 2: 0.0%Top
- Granite 4.2 8B: 0.0%Top
SciCode
Scientific computing in Python
- Mercury 2: 37.7%Top
- Granite 4.2 8B: 31.5%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Mercury 2: 26.5%
- Granite 4.2 8B: —
τ²-Bench Telecom
Tool use in a customer-support simulation
- Mercury 2: 70.8%
- Granite 4.2 8B: —
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Mercury 2: 43.7%
- Granite 4.2 8B: 45.0%Top
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.
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
Related models
Other Inception models, starting with the same family.