ModelsCompareBest forBenchmarksStatusPricingAPI

GPT-5.5 Pro

OpenAI·Operational·Released 2026-04-23textvision
Context1,050k
Max output128k
Input / 1M$30 ↗
Output / 1M$180 ↗
Cached in-
Benchmarks8

Benchmarks

Cited public sources · rank is exact-benchmark, apples-to-apples

FrontierMath Tier 4 v2 (Epoch AI run)#4/4478% ↗
FrontierMath Tiers 1-3 v2 (Epoch AI run)#4/5987.7% ↗
BrowseComp#1/1590.1% ↗
FrontierMath Tier 1-3#1/352.4% ↗
FrontierMath Tier 4#1/339.6% ↗
GDPval (wins or ties)#3/682.3% ↗
Humanity's Last Exam (no tools)#7/2943.1% ↗
Humanity's Last Exam (with tools)#5/1357.2% ↗

Compare

vs GPT-6 Astravs GPT-5.6 Solvs GPT-5.6 Terravs GPT-5.6 Lunavs Claude Fable 5.1vs Claude Opus 5vs Claude Sonnet 5vs Claude Haiku 4.5

More from OpenAI

GPT-6 AstraGPT-5.6 SolGPT-5.6 TerraGPT-5.6 LunaGPT-5.5GPT-5.4

Access GPT-5.5 Pro and every other model through one endpoint with automatic failover: Respan gateway.