GPT-5.5 (high)

GPT-5.5 (high)

OpenAI · Released Apr 23, 2026 Frontier New Top Pick
Intelligence #7 / 557
86.7 Our Score
Speed #168 / 259
63.4 tokens / sec
Input #526 / 560
$5.00 per 1M tokens
Output #534 / 560
$30.00 per 1M tokens
Context
Not reported

Analysis Summary

GPT-5.5 (high) sits in the Frontier tier on our leaderboard, ranked #7 of 557 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 high from OpenAI scores 58.9 on intelligence and 58.5 on coding with a 76.4 agentic index, placing it just behind the full GPT-5.5 flagship across all capability dimensions.

Assessed May 14, 2026

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

Performance Profile

Intelligence9.8Technical9.9Value4.5Content9.6
Intelligence 9.8/10
Technical 9.9/10
Content 9.6/10
Value 4.5/10

Performance Indices

Source: Artificial Analysis

58.9 Intelligence Index
58.5 Coding Index
76.4 Agentic Index

Benchmark Scores

Intelligence

GPQA Diamond 93.2% Graduate-level scientific reasoning
HLE 43% Humanity's Last Exam
SciCode 55.9% Scientific computing

Technical

TerminalBench Hard 59.8% Agentic terminal tasks
τ²-Bench 93% Conversational agent benchmark

Content

IFBench 71.6% Instruction following
LCR 73.3% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does GPT-5.5 (high) 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

Leaderboard Categories