OpenAI
gpt-5.5-pro
proprietaryMultimodal
Benchmark Average (0–100)
73.7%
Average of non-null benchmark scores across all evaluated tasks.
BENCHMARK SCORES
BrowseComp90.1%
BrowseComp tests web browsing comprehension, measuring ability to find and synthesize information from websites.
HLE57.2%
Humanity's Last Exam (HLE) is a multi-modal benchmark testing frontier knowledge across mathematics, humanities, and natural sciences with 2,500 expert-level questions.
OTHER BENCHMARKS
FrontierMath
39.6%
MODEL INFO
Organization
OpenAI
Context Window
—
Release Date
2026-04-23
Knowledge Cutoff
2025-12-01
Parameters
—
License
proprietary
METADATA
Announcement Date
2026-04-23
Organization Country
US
Canonical ID
—