Docs
Search
Ctrl K
Models
Chat
Compare
Providers
Apps
Rankings
Expert SWE Benchmark Leaderboard | Phaseo
Expert SWE
Expert SWE
AI benchmark results and model performance
Summary
▼
Summary
▼
Type: percentage
Code
View benchmark source
Recorded Results
1
Average Score
73.10%
Scores Over Time
Individual benchmark scores plotted by date.
Models Using This Benchmark
Organisation
Model
Reported
Top Score
Info
Self Reported
Source
OpenAI
GPT 5.5
23 Apr 2026
73.10%
Internal
Yes
Source
Score Range
73.10% - 73.10%
Leading Model (lowest score)
73.10% - GPT 5.5
Sign Up
Sign Up