Inference
EN
OpenAI

GPT-5.5 Pro

GPT-5.5 Pro is a reasoning model from OpenAI in the GPT-5.5 family. 12 benchmarks count toward its index, in 4 categories.

  • Closed weights
  • Reasoning
  • Input: file · image · text
  • Released 2026-04
RankedEnough results for an index.
IndexAll categories, out of 100.74.8±8.7Median 51.0
CoverageIndex weight that has results.60%
SpeedOutput tokens per second.19/sMedian 67/s
First tokenSeconds to the first output token.9.1 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$30.00batch $15.00Median $0.60
Output / 1MUS dollars per 1M output tokens.$180.00batch $90.00 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.1.05MMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
openai/gpt-5.5-pro
Max outputMaximum output tokens per request.
128K
Knowledge cutoffLast date of training data.
1 Dec 2025
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
—
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
1 provider
ProviderTypeMaker, cloud, host or router.InputOutputContext
OpenRouterRouter$30.00$180.001.05M

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.1 counted71.1—
CodingCode writing and repair.None counted——
ReasoningLogic problems and puzzles.4 counted81.16 / 227
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.2 counted69.024 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.5 counted76.38 / 168

Results

12 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
OTIS Mock AIME 2024-2025Math100.0%1 / 200
FrontierMath-2025-02-28-PrivateMath51.0% ±2.92 / 69
FrontierMath-Tier-4-2025-07-01-PrivateMath39.6% ±7.12 / 55
Critical Physics TasksReasoningAbove fitFar above this model's index.30.6%9 / 214
GPQA diamond · Epoch AIKnowledge93.9% ±1.614 / 217
Chess PuzzlesReasoning62.0% ±4.98 / 90
ARC-AGI-2 (semi-private)Reasoning84.2%16 / 131
FrontierMath-Tiers-1-3-v2-PrivateMath87.7% ±1.911 / 90
Humanity's Last ExamKnowledge57.2%11 / 77
ARC-AGI-1 (semi-private)Reasoning95.0%19 / 126
BrowseCompAgentic90.1%10 / 63
FrontierMath-Tier-4-v2-PrivateMath78.0% ±6.512 / 72
Humanity's Last Exam without toolsKnowledge43.1%23 / 53
ARC-AGI-1 (public eval)Reasoning98.0%11 / 116
ARC-AGI-2 (public eval)Reasoning90.4%15 / 122

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseEpoch AICC BYARC Prize FoundationTerms restrict reusemodels.devMIT

History

5 releases
Index76.1 → 74.8
23 Oct 202612 Nov 2026
Output / 1M$180.00 → $180.00
23 Oct 202612 Nov 2026

Questions

How much does GPT-5.5 Pro cost?
$30.00 per 1M input tokens, $180.00 per 1M output tokens.
How good is GPT-5.5 Pro?
Its index is 74.8 out of 100. That is place 12 of 283 ranked models.
What is GPT-5.5 Pro best at?
Reasoning: 81.1 out of 100, place 6 of 227.
How fast is GPT-5.5 Pro?
19 output tokens per second, 9.1 s to the first token.
What is the context window of GPT-5.5 Pro?
1.05M tokens.
Is GPT-5.5 Pro open source?
No. Its weights are not published.
When was GPT-5.5 Pro released?
April 2026.

Badge

GPT-5.5 Pro on Inference360: place 12 of 283, index 74.8
HTML
<a href="https://inference360.ai/models/gpt-5-5-pro"><img src="https://inference360.ai/badges/gpt-5-5-pro.svg" alt="GPT-5.5 Pro on Inference360: place 12 of 283, index 74.8" height="20"></a>
Markdown
[![GPT-5.5 Pro on Inference360: place 12 of 283, index 74.8](https://inference360.ai/badges/gpt-5-5-pro.svg)](https://inference360.ai/models/gpt-5-5-pro)

Compare with

Claude Fable 574.0Kimi K3.1 Pro75.7Claude Opus 573.8Claude Fable 5.176.2GPT-5.4 Pro73.3

Lower price

Hy472.0 · $1.25/1MGPT-6.1 Terra77.1 · $5.00/1MGemini 4 Carbon82.7 · $10.00/1M

More from OpenAI

All models
GPT-5.569.1GPT Audio 1.5UnrankedGPT-5.4 Image 2UnrankedGPT Mini LatestUnrankedGPT Chat LatestUnranked