New: Agent Index for knowledge work is live.Explore the index ↗
Compare models

Explore GPT-5.5 Pro’s published benchmark results and provider offerings below. More comparable task results are needed to describe its strongest areas.

Updated: Data as of:
Compare this model

Strongest results

More comparable benchmark results are needed.

Model details

Proprietary1 benchmarks
Specifications for GPT-5.5 Pro
ModelGPT-5.5 Pro
Agent Index v1.2Insufficient coverage (0/7) · Preview
CreatorOpenAI (opens in a new tab)
AvailabilityProprietary
Context size922,000 tokens (opens in a new tab)
Max output128,000 tokens (opens in a new tab)
Knowledge cutoffNot reported
LicenseNot reported

Pricing and performance

Per provider and reported configuration. Prices are USD per 1M tokens.

Provider offerings for GPT-5.5 Pro
Provider / configurationContexttokensInputUSD / 1M tokensOutputUSD / 1M tokensLatencyTTFT · secondsSpeedtokens / sec
OpenAI (opens in a new tab)
Official standard API pricing		922,000$30.00 (opens in a new tab)$180.00 (opens in a new tab)Not reportedNot reported

Reported benchmarks

All published results in our dataset, with versions, evaluation settings, and sources.

All published benchmark reports for GPT-5.5 Pro
BenchmarkScoreEvaluation setupSource
Humanity's Last ExamStable HLE — full setAccuracy · Higher is better57.2%Reasoning effort xhigh; research environment. · subset: full · Tools enabledOpenAI ↗ (opens in a new tab)provider reported · 2026-04-23
Humanity's Last ExamStable HLE — full setAccuracy · Higher is better43.1%Reasoning effort xhigh; research environment. · subset: full · No toolsOpenAI ↗ (opens in a new tab)provider reported · 2026-04-23