NOUMENOpen app
NOUMEN

Meta · Open weights

Steelskull Electra R1 70b

Added Jan 1, 2024Open weights

Compare models

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

Loading models…

Use in the app

Steelskull Electra R1 70b

Input
Text
Output
Text
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.70
Output
$0.70

Reference prices as published by the model provider. API example

Specifications

Context window
32.8K
Max output
—

Side by side

Steelskull Electra R1 70b 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…

Steelskull Electra R1 70bMetaThis modelMuse WonderMetaRemove
ProviderMetaMeta
Discovery tierOpen weightsFrontier
AddedJan 1, 2024Oct 12, 2026
Limits
Context window32.77K1.05MBest
Average output—1.2K tokens
Pricing, USD per 1M tokens
Input$0.70Best$4.00
Output$0.70Best$20.00
Cache read—$0.20
Performance
Throughput—124.6 tok/s
Time to first token—4.4 s
Request success (24h)—99.3%
Benchmark indexes
Intelligence Index—52.4
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Structured outputNoYes
PDF inputNoYes
Audio inputNoYes
Video inputNoYes
Reasoning effort—minimal, low, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • Steelskull Electra R1 70b
  • Muse Wonder

Intelligence Index

  • Steelskull Electra R1 70b—
  • Muse Wonder52.4
3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 68.1%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 39.1%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 10.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 1,659 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 1,770 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 30.6%

  • AA-LCRv1.1

    Reasoning across long documents

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 80.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 22.2%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 50.1%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 52.0%

  • SciCode

    Scientific computing in Python

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 60.3%

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • Steelskull Electra R1 70b: —
    • Muse Wonder: 80.7%

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.

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": "Steelskull/L3.3-Electra-R1-70b",
    "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="Steelskull/L3.3-Electra-R1-70b",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Meta

Other Meta models, starting with the same family.