Model

GPT-5.5

CLOSED

OpenAI · GPT-5.5 family · released Apr 23, 2026

Codename Spud; ChatGPT/Codex launched Apr 23, 2026 with API following ~1 day later once safeguards were finalized.

ReasoningCodingVisionFunction callingTool useAgentic

2589.8

Elo · rank #31

Parameters

Undisclosed

Active params

—

Context

1.05M tokens

Architecture

Undisclosed architecture (presumed dense transformer, reasoning-tuned); codename "Spud"; Thinking + Pro tiers

License

Proprietary

Languages

—

API price (in/out)

$5 / $30

Modalities

text · vision

Benchmark results

Bar shows position within the tracked field; marker = field best

ARC-AGI-2Reasoning85.0%#7

best: GPT-6 Astra · 95.0%

BrowseCompAgents84.4%#10

best: Kimi K3 · 91.2%

CyberGymCoding81.8%#8

best: MiMo-V2.6-Flash · 95.1%

FrontierMath (Tiers 1-3)Math51.7%#5

best: GPT-5.6 Sol · 89.0%

FrontierMath (Tier 4)Math35.4%#5

best: GPT-5.6 Sol · 83.0%

GDPvalAgents84.9%#2

best: Seed 2.1 Pro · 87.9%

GPQA DiamondReasoning93.6%#8

best: GPT-6 Astra · 96.0%

Humanity's Last ExamReasoning41.4%#29

best: Claude Opus 5.5 · 67.7%

LiveCodeBenchCoding85.3%#24

best: DeepSeek-V4-Pro (Think Max) · 93.5%

OSWorld-VerifiedAgents78.7%#9

best: Claude Fable 5 · 85.0%

SWE-bench ProCoding58.6%#22

best: Claude Opus 5.5 · 89.9%

SWE-bench VerifiedCoding82.6%#17

best: Claude Opus 5 · 97.0%

τ²-Bench TelecomAgents98.0%#9

best: Claude Opus 4.6 · 99.3%

Terminal-Bench 2.0Coding82.7%#19

best: DeepSeek-V4.1-Flash · 90.6%

Run it locally

Closed weights — available via API only. No local deployment.

Input / M tok

Output / M tok

$30

GPT-5.5 family

Elo progression across releases

GPT-5.5Apr 20262589.8 GPT-5.5 (High)Apr 20262533.9 GPT-5.5 (xHigh)Apr 20262608.5

Resources

DOCSplatform.openai.com/docs/models/gpt-5.5 APIAvailable via OpenAI API

API price $5/$30 · each benchmark row carries its own source badge (see methodology)