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

2680.9

Elo · rank #8

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%#2

best: GPT-5.6 · 92.5%

BrowseCompAgents84.4%#7

best: Kimi K3 · 91.2%

CyberGymCoding81.8%#2

best: GPT-5.6 · 84.5%

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

best: GPT-5.6 · 89.0%

FrontierMath (Tier 4)Math35.4%#3

best: GPT-5.6 · 83.0%

GDPvalAgents84.9%#2

best: Seed 2.1 Pro · 87.9%

GPQA DiamondReasoning93.6%#6

best: GPT-5.6 · 94.6%

Humanity's Last ExamReasoning41.4%#21

best: Claude Sonnet 5 · 57.4%

LiveCodeBenchCoding85.3%#21

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

OSWorld-VerifiedAgents78.7%#5

best: Claude Fable 5 · 85.0%

SWE-bench ProCoding58.6%#11

best: Claude Fable 5 · 80.0%

SWE-bench VerifiedCoding82.6%#7

best: Claude Fable 5 · 95.0%

τ²-Bench TelecomAgents98.0%#9

best: Claude Opus 4.6 · 99.3%

Terminal-Bench 2.0Coding82.7%#6

best: GPT-5.6 · 88.8%

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 20262680.9 GPT-5.5 (High)Apr 20262563.6 GPT-5.5 (xHigh)Apr 20262725.9

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)