NOUMENOpen app
NOUMEN

OpenAI · Frontier

GPT Latest

Added Mar 29, 2026

Compare models

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

Loading models…

Use in the app

Compatibility alias that routes to GPT 6 Astra, the newest GPT flagship for complex reasoning, coding, and agentic workflows.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
Input
Text, Images
Output
Text
Reasoning effort
low · medium · high · xhigh · max
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$10.00
Output
$50.00
Cache read
$1.00
Cache write
$12.50

Reference prices as published by the model provider. API example

Specifications

Context window
1.1M
Max output
128K
Average output (7 days)
311 tokens
Longer than 33% of 465 models

Side by side

GPT Latest 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…

GPT LatestOpenAIThis modelGPT 4.1OpenAIRemove
ProviderOpenAIOpenAI
Discovery tierFrontierFrontier
AddedMar 29, 2026Sep 10, 2025
Limits
Context window1.05MBest1.05M
Max output128KBest32.77K
Average output311 tokens29 tokens
Pricing, USD per 1M tokens
Input$10.00$2.00Best
Output$50.00$8.00Best
Cache read$1.00$0.50Best
Cache write$12.50—
Performance
Throughput112.2 tok/s—
Time to first token24.3 s—
Request success (24h)97.3%100.0%Best
Benchmark indexes
Intelligence Index49.6Best12.7
Coding Index76.7—
Math Index—34.7
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesYes
Reasoning effortlow, medium, high, xhigh, max—

Public evaluations

Benchmarks

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

  • GPT Latest
  • GPT 4.1

Intelligence Index

  • GPT Latest49.6
  • GPT 4.112.7

GPT Latest tested at medium reasoning effort

GPT Latest: Better than 96% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT Latest: 76.7
    • GPT 4.1: —

  • Math Index

    Composite of the math evaluations

    • GPT Latest: —
    • GPT 4.1: 34.7

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT Latest: 64.6%
    • GPT 4.1: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT Latest: 33.6%
    • GPT 4.1: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GPT Latest: 1,460 Elo
    • GPT 4.1: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT Latest: 1,487 Elo
    • GPT 4.1: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT Latest: 30.4%
    • GPT 4.1: —

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT Latest: 79.7%Top
    • GPT 4.1: 68.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • GPT Latest: 38.3%
    • GPT 4.1: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT Latest: 52.7%Top
    • GPT 4.1: 4.2%

  • GPQA Diamond

    Graduate-level science questions

    • GPT Latest: 93.9%Top
    • GPT 4.1: 66.6%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GPT Latest: —
    • GPT 4.1: 80.6%

  • IFBench

    Following precise output instructions

    • GPT Latest: —
    • GPT 4.1: 43.0%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT Latest: 49.5%
    • GPT 4.1: —

  • SciCode

    Scientific computing in Python

    • GPT Latest: 54.2%
    • GPT 4.1: —

  • LiveCodeBench

    Recent competitive programming problems

    • GPT Latest: —
    • GPT 4.1: 45.7%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GPT Latest: —
    • GPT 4.1: 34.7%

  • AIME

    Competition mathematics

    • GPT Latest: —
    • GPT 4.1: 43.7%

  • MATH-500

    Competition math problems

    • GPT Latest: —
    • GPT 4.1: 91.3%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT Latest: —
    • GPT 4.1: 13.6%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT Latest: —
    • GPT 4.1: 47.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT Latest: 79.7%Top
    • GPT 4.1: 68.3%

Scores from Artificial Analysis, updated Oct 26, 2026. GPT Latest was tested at medium reasoning effort; compare scores measured at the same effort.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.

Throughput
112.2 tok/s
Faster than 64% of 247 models
Time to first token
24.3 s
Quicker than 0% of 247 models
Request success (24h)
97.6%
Reliable
Hourly request success · last 72 hoursLowest hour 80.0%
  • 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": "openai/gpt-latest",
    "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="openai/gpt-latest",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.