#19
GPT-5.5 Pro
gpt-5.5-proHelpfulness
Instruction
Following
Comprehension
Empathy
Creative
Writing
Helpfulness
0.0
Instruction Following
0.0
Comprehension
0.0
Empathy
0.0
Creative Writing
0.0
Speed
Avg 48 tok/s
Release Date
April 23, 2026
Lab
OpenAI
Type
Proprietary
Context Size
1.1M
Max Output Tokens
128K
Cost per 1 million tokens
$30.00 / $180.00
Model Inputs*
Text, Images
Model Outputs*
Text
Tool Calling*
Enabled
Overall Assistant Score
An average score combining the 5 main categories.
89.30 pts
Rank #19
74th Percentile
0
Novice
33
Capable
66
Proficient
100
Expert
GPT-5.5 Pro spends extra compute on hard assistant tasks—dense documents, strict instructions, and long back-and-forth where mistakes are costly. Our tests show gains in instruction following and comprehension over standard GPT-5.5. Empathy stays cool. Creative writing gets worse under heavier reasoning: parallel internal drafts and compressed scratchpads produce drier, sometimes tone-fractured prose. Use it when correctness on a high-stakes ask matters more than warmth or literary quality.
Overall Score vs Price
Price axis is logarithmic (USD per 1M input tokens) · Higher score and lower price is better
Ringed point is this model
Anthropic
DeepSeek
Google
Meta
Moonshot
OpenAI
SpaceX AI
Zhipu AI
Intelligence
Overall Score · Higher is better
Speed
Output tokens per second · Higher is better
Price
USD per 1M input tokens · Lower is better
OpenAI Models
Overall Score · Same provider
GPT Family
Overall Score · Same model family
Closest Rivals
Overall Score · Nearest by overall rank