#1 ranked model today
Context
400K tokens (~200 books)
Input $/1M
$30.00
Output $/1M
$180.00
Type
text
License
Proprietary
Benchmarks
3 tested
Data updated today
About
GPT-5.5 Pro · OpenAI's highest-capability tier. Tops BrowseComp (90.1%), FrontierMath T1-3 (52.4%), GPQA Diamond (94.2%). $30/$180 per 1M tokens.
Tested on 3 benchmarks with 87.8% average. Top scores: GPQA diamond (94.2%), browsecomp (90.1%), mcp-atlas (79.1%).
Looking for similar performance at lower cost?
Qwen3.5 397B A17B scores 96.3 (96% as good) at $0.39/1M input · 99% cheaper
Qwen3.5 397B A17B scores 96.3 (96% as good) at $0.39/1M input · 99% cheaper
Capabilities
knowledge
94.2
#1 globally
other
84.6
#1 globally
Benchmark Scores
Compare AllTested on 3 benchmarks · Ranked across 2 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
knowledgeCompare knowledge →
GPQA diamond
94.2—Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Research
Documentation
Community
BenchGecko API
gpt-5-5-pro
Specifications
- Typetext
- Context400K tokens (~200 books)
- ReleasedApr 2026
- LicenseProprietary
- StatusActive
- Cost / Message~$0.240
Available On
Learn More
Share & Export
Frequently Asked Questions
GPT-5.5 Pro is a proprietary text AI model by OpenAI, released in April 2026. It has an average benchmark score of 99.9. Context window: 400K tokens.