NOUMENOpen app
NOUMEN

OpenAI · Balanced

GPT-3.5 Turbo

Added Jan 1, 2024

Compare models

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

Loading models…

Use in the app

Older model. Brought ChatGPT to the mainstream, seen as dated nowadays. 90% cheaper than GPT-4-Turbo, recommended for very simple tasks.

Input
Text
Output
Text
Discovery tier
Balanced

Pricing

USD per 1M tokens
Input
$0.50
Output
$1.50

Reference prices as published by the model provider. API example

Specifications

Context window
16.4K
Max output
4.1K

Side by side

GPT-3.5 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-3.5 TurboOpenAIThis modelReka Flash 3rekaRemove
ProviderOpenAIreka
Discovery tierBalancedOpen weights
AddedJan 1, 2024Oct 15, 2026
Limits
Context window16.39K65.54KBest
Max output4.1K65.54KBest
Average output—2.7K tokens
Pricing, USD per 1M tokens
Input$0.50$0.11Best
Output$1.50$0.21Best
Performance
Request success (24h)—100.0%
Benchmark indexes
Intelligence Index5.55.6Best
Coding Index10.7—
Math Index—33.7
Capabilities
ReasoningNoYes
Structured outputNoYes
Reasoning effort——

Public evaluations

Benchmarks

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

  • GPT-3.5 Turbo
  • Reka Flash 3

Intelligence Index

  • GPT-3.5 Turbo5.5
  • Reka Flash 35.6

GPT-3.5 Turbo: Better than 1% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT-3.5 Turbo: 10.7
    • Reka Flash 3: —

  • Math Index

    Composite of the math evaluations

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 33.7

Document reasoning

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 0.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 4.4%

  • GPQA Diamond

    Graduate-level science questions

    • GPT-3.5 Turbo: 29.7%
    • Reka Flash 3: 52.9%Top

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GPT-3.5 Turbo: 46.2%
    • Reka Flash 3: 66.9%Top

  • IFBench

    Following precise output instructions

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 30.4%

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 43.5%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 33.7%

  • AIME

    Competition mathematics

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 51.0%

  • MATH-500

    Competition math problems

    • GPT-3.5 Turbo: 44.1%
    • Reka Flash 3: 89.3%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 0.0%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 0.0%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT-3.5 Turbo: —
    • Reka Flash 3: 0.0%

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-3.5-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-3.5-turbo",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.