Benchmark menu

Model detail

GPT-5.5

A static, shareable model page that remains complete without JavaScript.

GPT-5.5

Provider: OpenAI · Public slug: gpt-5-5

Rank
6
Rank movement
Baseline
Score
48.9
Last measured
2026-07-05
Coverage
Complete coverage

Reasoning scores

XHigh
67.6
Medium
47.2
None
31.8

Generation health

XHigh88%0%12%n 8Medium88%12%0%n 8None88%0%12%n 8 Complete coverage

Cost summary

Mean standard list-price equivalent
$1.11
Median unique-cell cost
$0.42
Unique-cell range
$0.12–$4.42
Coverage
24 unique cells / 24 observed runs
Observed-run total
$26.57
Evidence basis
Standard list-price estimate
Mean output
35k tok
Output range
2.8k–145k tok
Token samples
24

Cost means equal-weight unique model/game/reasoning cells. Provider-account billed spend is reported separately on Charts.

Run setup

  • Overall Models: combines public reasoning variants
  • Standard GameBench code-generation prompt