Language modelPro only

GPT-5.5 Pro

OpenAI

Released: April 23, 2026
Data date: September 8, 2026
Predecessor: GPT-5.4 Pro

Price: $30 · $180
Input · Output / 1M tokens
Input: Text, Image
Output: Text

GPT-5.5 Pro is the Pro version of the GPT-5.5 family for especially demanding tasks. OpenAI describes it as a research partner for difficult work and documents a 1.05 million token context window.

GPT-5.4 Pro was the previous Pro tier. OpenAI reports more comprehensive and useful responses in early testing, but it does not publish one consistent metric for this pair.

Profile

Specifications and access

Published information about this model. Existing estimates are explicitly labeled.

Dated documentation and model-card observations. Provider limits, native context and extended context can differ. Configuration notes retain the source wording.

Specification	Value and source
Weights	ProprietarySource
Access	APISource
Context window	1,050,000 tokensSource
Knowledge cutoff	December 1, 2025Source
Notes	Pro-tier research partner variant, higher accuracy, FrontierMath Tier 4 39.6%Source
API model ID	gpt-5.5-proSource
Maximum output	128,000 tokensSource
Input	Text, ImageSource
Output	TextSource
Reasoning mode	medium, high, xhighSource
API interfaces	Responses APISource
Tool calling	YesSource
Structured output	YesSource
Release	2026-04-23Source

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

GDPval (Show measurement, test conditions, and source)

Source value: 82.3
Score: 82.3
Metric: percent
Unit: %
Category: Professional
Direction: Higher is better
Comparison cohort: research:gpt-5.5-pro:0
Source type: vendor-reported
Evaluator: OpenAI
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GPT-5.5 Pro; wins or ties; xhigh
Context: OpenAI notes evaluations were run in a research environment.

Source OpenAI

Investment Banking Modeling Tasks (Show measurement, test conditions, and source)

Source value: 88.6
Score: 88.6
Metric: percent
Unit: %
Category: Professional
Direction: Higher is better
Comparison cohort: research:gpt-5.5-pro:1
Source type: vendor-reported
Evaluator: OpenAI
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GPT-5.5 Pro; internal; xhigh
Context: OpenAI notes evaluations were run in a research environment.

Source OpenAI

BrowseComp (Show measurement, test conditions, and source)

Source value: 90.1
Score: 90.1
Metric: percent
Unit: %
Category: Tool use
Direction: Higher is better
Comparison cohort: research:gpt-5.5-pro:2
Source type: vendor-reported
Evaluator: OpenAI
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GPT-5.5 Pro; tool use; xhigh
Context: OpenAI notes evaluations were run in a research environment.

Source OpenAI

GeneBench (Show measurement, test conditions, and source)

Source value: 33.2
Score: 33.2
Metric: percent
Unit: %
Category: Academic
Direction: Higher is better
Comparison cohort: research:gpt-5.5-pro:3
Source type: vendor-reported
Evaluator: OpenAI
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GPT-5.5 Pro; academic; xhigh
Context: OpenAI notes evaluations were run in a research environment.

Source OpenAI

FrontierMath Tier 1-3 (Show measurement, test conditions, and source)

Source value: 52.4
Score: 52.4
Metric: percent
Unit: %
Category: Academic
Direction: Higher is better
Comparison cohort: research:gpt-5.5-pro:4
Source type: vendor-reported
Evaluator: OpenAI
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GPT-5.5 Pro; academic; xhigh
Context: OpenAI notes evaluations were run in a research environment.

Source OpenAI

FrontierMath Tier 4 (Show measurement, test conditions, and source)

Source value: 39.6
Score: 39.6
Metric: percent
Unit: %
Category: Academic
Direction: Higher is better
Comparison cohort: research:gpt-5.5-pro:5
Source type: vendor-reported
Evaluator: OpenAI
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GPT-5.5 Pro; academic; xhigh
Context: OpenAI notes evaluations were run in a research environment.

Source OpenAI

Humanity's Last Exam (Show measurement, test conditions, and source)

Source value: 43.1
Score: 43.1
Metric: percent
Unit: %
Category: Academic
Direction: Higher is better
Comparison cohort: research:gpt-5.5-pro:6
Source type: vendor-reported
Evaluator: OpenAI
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GPT-5.5 Pro; no tools; xhigh
Context: OpenAI notes evaluations were run in a research environment.

Source OpenAI

Humanity's Last Exam (Show measurement, test conditions, and source)

Source value: 57.2
Score: 57.2
Metric: percent
Unit: %
Category: Academic
Direction: Higher is better
Comparison cohort: research:gpt-5.5-pro:7
Source type: vendor-reported
Evaluator: OpenAI
Status: active
Retrieved at: 2026-09-08
Methodology: Vendor-reported result. GPT-5.5 Pro; with tools; xhigh
Context: OpenAI notes evaluations were run in a research environment.

Source OpenAI

Model generations

Predecessor and successor

Every relationship names its kind, its qualification and the dated source it rests on.

Evidence

Sources and data date

Every statement links to its underlying documentation or leaderboard.

Type	Evidence and data date
Price	Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs. Source: Pricing · API pricing
Input	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · GPT-5.5 Pro API model documentation · Editorial description reviewed October 2, 2026
Output	Documented modalities. Retrieved September 8, 2026. Source: Model documentation · Model metadata (retrieved September 8, 2026) · GPT-5.5 Pro API model documentation · Editorial description reviewed October 2, 2026
Research status	Research date September 8, 2026. 3 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Not found in the inspected sources	parameters-billions Original wording OpenAI does not publish parameter counts.
Not found in the inspected sources	independent-benchmarks Original wording The release page's exact model columns are vendor-reported; no independent row was added.
Unresolved	AA benchmark rows Original wording No exact Artificial Analysis model page located in the checked public sitemap.
Additional source	OpenAI (retrieved September 8, 2026) · Introducing GPT-5.5 · Editorial description reviewed October 2, 2026
Additional source	OpenRouter: Popularity index (derived), CC BY 4.0
Additional source	Vercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional source	Creative Commons Attribution 4.0

GPT-5.5 Pro

Specifications and access

Measurements without matching peer values

Our tests

Pelican on a bicycle

Popularity

Published prices

Predecessor and successor

Sources and data date