NOUMENOpen app
NOUMEN

OpenAI · Frontier

GPT Chat Latest

Added May 3, 2026

Compare models

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

Loading models…

Use in the app

Compatibility chat alias that routes to GPT 5.6 Sol, the flagship GPT-5.6 tier for complex reasoning, coding, and agentic workflows.

  • Reasoning
  • Tools
  • Vision
  • Structured output
  • PDF input
Input
Text, Images
Output
Text
Reasoning effort
none · low · medium · high · xhigh · max
Discovery tier
Frontier

Pricing

USD per 1M tokens
Input
$2.00
Output
$10.00
Cache read
$0.20
Cache write
$2.50

Reference prices as published by the model provider. API example

Specifications

Context window
1.1M
Max output
128K
Average output (7 days)
408 tokens
Longer than 40% of 465 models

Side by side

GPT Chat 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 Chat LatestOpenAIThis modelGPT 5.2OpenAIRemove
ProviderOpenAIOpenAI
Discovery tierFrontierFrontier
AddedMay 3, 2026Dec 11, 2025
Limits
Context window1.05MBest400K
Max output128K128K
Average output408 tokens172 tokens
Pricing, USD per 1M tokens
Input$2.00$1.75Best
Output$10.00Best$14.00
Cache read$0.20$0.18Best
Cache write$2.50—
Performance
Throughput41.4 tok/s—
Time to first token9.0 s—
Request success (24h)100.0%100.0%
Benchmark indexes
Intelligence Index47.0Best17.0
Coding Index77.4—
Math Index—51.0
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
PDF inputYesYes
Reasoning effortnone, low, medium, high, xhigh, maxnone, low, medium, high, xhigh

Public evaluations

Benchmarks

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

  • GPT Chat Latest
  • GPT 5.2

Intelligence Index

  • GPT Chat Latest47.0
  • GPT 5.217.0

GPT Chat Latest tested at max reasoning effort

GPT Chat Latest: Better than 94% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • GPT Chat Latest: 77.4
    • GPT 5.2: —

  • Math Index

    Composite of the math evaluations

    • GPT Chat Latest: —
    • GPT 5.2: 51.0

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • GPT Chat Latest: 60.1%
    • GPT 5.2: —

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • GPT Chat Latest: 30.3%
    • GPT 5.2: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • GPT Chat Latest: 1,479 Elo
    • GPT 5.2: —

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • GPT Chat Latest: 1,609 Elo
    • GPT 5.2: —

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • GPT Chat Latest: 27.2%
    • GPT 5.2: —

  • AA-LCRv1.1

    Reasoning across long documents

    • GPT Chat Latest: 84.0%Top
    • GPT 5.2: 45.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • GPT Chat Latest: 30.0%
    • GPT 5.2: —

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • GPT Chat Latest: 49.5%Top
    • GPT 5.2: 8.0%

  • GPQA Diamond

    Graduate-level science questions

    • GPT Chat Latest: 94.1%Top
    • GPT 5.2: 71.2%

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • GPT Chat Latest: —
    • GPT 5.2: 81.4%

  • IFBench

    Following precise output instructions

    • GPT Chat Latest: 72.7%Top
    • GPT 5.2: 47.4%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • GPT Chat Latest: 39.9%
    • GPT 5.2: —

  • SciCode

    Scientific computing in Python

    • GPT Chat Latest: 57.1%
    • GPT 5.2: —

  • LiveCodeBench

    Recent competitive programming problems

    • GPT Chat Latest: —
    • GPT 5.2: 66.9%

Math

  • AIME 2025

    Competition mathematics, 2025 problems

    • GPT Chat Latest: —
    • GPT 5.2: 51.0%

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • GPT Chat Latest: 65.9%Top
    • GPT 5.2: 31.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • GPT Chat Latest: 85.1%Top
    • GPT 5.2: 46.5%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • GPT Chat Latest: 84.0%Top
    • GPT 5.2: 45.7%

Scores from Artificial Analysis, updated Oct 26, 2026. GPT Chat Latest was tested at max 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
41.4 tok/s
Faster than 30% of 247 models
Time to first token
9.0 s
Quicker than 11% of 247 models
Prompt cache hits
0.0%
About $2.00 per 1M input tokens with caching
Request success (24h)
100.0%
Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 83.3%
  • 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-chat-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-chat-latest",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

OpenAI

Other OpenAI models, starting with the same family.