NOUMENOpen app
NOUMEN

OpenAI · Balanced

GPT-4 Turbo

Added Jan 1, 2024

Compare models

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

Loading models…

Use in the app

Can take in the largest messages (up to 300 pages of context), and all round seen as one of the best in class models.

  • Vision
Input
Text, Images
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$10.00
Output
$30.00

Reference prices as published by the model provider. API example

Specifications

Context window
128K
Max output
4.1K

Side by side

GPT-4 Turbo 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-4 TurboOpenAIThis modelNvidia Nemotron 70bnvidiaRemove
ProviderOpenAInvidia
Discovery tierBalancedOpen weights
AddedJan 1, 2024Apr 15, 2025
Limits
Context window128KBest16.38K
Max output4.1K8.19KBest
Pricing, USD per 1M tokens
Input$10.00$0.36Best
Output$30.00$0.41Best
Performance
Request success (24h)—22.9%
Benchmark indexes
Intelligence Index7.0Best6.9
Coding Index21.5—
Math Index—11.0
Capabilities
VisionYesNo
Reasoning effort——

Public evaluations

Benchmarks

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

  • GPT-4 Turbo
  • Nvidia Nemotron 70b

Intelligence Index

  • GPT-4 Turbo7.0
  • Nvidia Nemotron 70b6.9

GPT-4 Turbo: Better than 9% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT-4 Turbo: 21.5
    • Nvidia Nemotron 70b: —

  • Math Index

    Composite of the math evaluations

    • GPT-4 Turbo: —
    • Nvidia Nemotron 70b: 11.0

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT-4 Turbo: —
    • Nvidia Nemotron 70b: 8.3%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT-4 Turbo: 3.1%
    • Nvidia Nemotron 70b: 4.2%Top

  • GPQA Diamond

    Graduate-level science questions

    • GPT-4 Turbo: —
    • Nvidia Nemotron 70b: 46.5%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GPT-4 Turbo: 69.4%Top
    • Nvidia Nemotron 70b: 69.0%

  • IFBench

    Following precise output instructions

    • GPT-4 Turbo: —
    • Nvidia Nemotron 70b: 30.7%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • GPT-4 Turbo: 29.1%Top
    • Nvidia Nemotron 70b: 16.9%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GPT-4 Turbo: —
    • Nvidia Nemotron 70b: 11.0%

  • AIME

    Competition mathematics

    • GPT-4 Turbo: 15.0%
    • Nvidia Nemotron 70b: 24.7%Top

  • MATH-500

    Competition math problems

    • GPT-4 Turbo: 73.7%Top
    • Nvidia Nemotron 70b: 73.3%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT-4 Turbo: —
    • Nvidia Nemotron 70b: 4.5%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT-4 Turbo: —
    • Nvidia Nemotron 70b: 23.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT-4 Turbo: —
    • Nvidia Nemotron 70b: 8.3%

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": "openai/gpt-4-turbo",
    "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-4-turbo",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.