GPT-5.5 (xhigh)

GPT-5.5 (xhigh)

OpenAI · Released Apr 23, 2026 Frontier New Top Pick
Intelligence #7 / 523
86.8 Our Score
AA Index #1 / 351
60.2 Artificial Analysis
Input #493 / 523
$5.00 per 1M tokens
Output #501 / 523
$30.00 per 1M tokens
Context
Not reported

Analysis Summary

GPT-5.5 (xhigh) sits in the Frontier tier on our leaderboard, ranked #7 of 523 published models on overall intelligence. At $5.00 input and $30.00 output per 1M tokens, it is among the most expensive on the market.

Editorial notes

GPT-5.5 XHigh from OpenAI leads the entire field on both intelligence and coding, with best-in-class instruction following, long-context reasoning, and agentic reliability; premium pricing is the only trade-off.

Assessed April 24, 2026

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence9.8Technical10Value4.5Content9.5
Intelligence 9.8/10
Technical 10/10
Content 9.5/10
Value 4.5/10

Performance Indices

Source: Artificial Analysis

60.2 Intelligence Index
59.1 Coding Index

This model was released recently. Independent benchmark evaluations are typically completed within days of release — these figures are preliminary and are likely to be updated as testing is finalised.

Benchmark Scores

Intelligence

GPQA Diamond 93.5% Graduate-level scientific reasoning
HLE 44.3% Humanity's Last Exam
SciCode 56.1% Scientific computing

Technical

TerminalBench Hard 60.6% Agentic terminal tasks
τ²-Bench 93.9% Conversational agent benchmark

Content

IFBench 75.9% Instruction following
LCR 74.3% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does GPT-5.5 (xhigh) stack up?

Compare side-by-side with other frontier models.

Compare Models

Model Information

ProviderOpenAI
Release Date April 23, 2026
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $5.00 $0.005000
Output $30.00 $0.030000