Inception · Efficient
Mercury Coder Small
Model by Inception AI. A diffusion large language model that runs incredibly quickly (500+ tokens/second) while matching Claude 3.5 Haiku and GPT-4o-mini. 1st in speed on Copilot arena, and matching 2nd in quality.
- Input
- Text
- Output
- Text
- Discovery tier
- Efficient
Pricing
USD per 1M tokens- Input
- $0.25
- Output
- $1.00
Reference prices as published by the model provider. API example
Specifications
- Context window
- 32.8K
- Max output
- 16.4K
Side by side
Mercury Coder Small compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Mercury Coder SmallInceptionThis model | Mercury 2InceptionRemove | |
|---|---|---|
| Provider | Inception | Inception |
| Discovery tier | Efficient | Balanced |
| Added | Jan 1, 2024 | Jan 1, 2024 |
| Limits | ||
| Context window | 32.77K | 128KBest |
| Max output | 16.38K | 50KBest |
| Pricing, USD per 1M tokens | ||
| Input | $0.25 | $0.25 |
| Output | $1.00 | $0.75Best |
| Cache read | — | $0.025 |
| Benchmark indexes | ||
| Intelligence Index | — | 10.8 |
| Coding Index | — | 31.1 |
| Capabilities | ||
| Reasoning | No | Yes |
| Tools | No | Yes |
| Structured output | No | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Mercury Coder Small
- Mercury 2
Intelligence Index
- Mercury Coder Small—
- Mercury 210.8
Indexes
Coding Index
Composite of the coding evaluations
- Mercury Coder Small: —
- Mercury 2: 31.1
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- Mercury Coder Small: —
- Mercury 2: 1.7%
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- Mercury Coder Small: —
- Mercury 2: 0.3%
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- Mercury Coder Small: —
- Mercury 2: 265 Elo
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- Mercury Coder Small: —
- Mercury 2: 494 Elo
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- Mercury Coder Small: —
- Mercury 2: 3.8%
AA-LCRv1.1
Reasoning across long documents
- Mercury Coder Small: —
- Mercury 2: 43.7%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Mercury Coder Small: —
- Mercury 2: 17.1%
GPQA Diamond
Graduate-level science questions
- Mercury Coder Small: —
- Mercury 2: 77.0%
IFBench
Following precise output instructions
- Mercury Coder Small: —
- Mercury 2: 69.8%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- Mercury Coder Small: —
- Mercury 2: 0.0%
SciCode
Scientific computing in Python
- Mercury Coder Small: —
- Mercury 2: 37.7%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- Mercury Coder Small: —
- Mercury 2: 26.5%
τ²-Bench Telecom
Tool use in a customer-support simulation
- Mercury Coder Small: —
- Mercury 2: 70.8%
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- Mercury Coder Small: —
- Mercury 2: 43.7%
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-coder-small",
"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-coder-small",
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.