Docs
Search
Ctrl K
Models
Chat
Compare
Providers
Apps
Rankings
AndroidWorld Benchmark Leaderboard | Phaseo
AndroidWorld
AndroidWorld
AI benchmark results and model performance
Summary
▼
Summary
▼
Type: percentage
Agents
Recorded Results
2
Average Score
78.80%
Score Range
75.70% - 81.90%
Leading Model (lowest score)
75.70% - GLM 5V Turbo
Scores Over Time
Individual benchmark scores plotted by date.
Models Using This Benchmark
Organisation
Model
Reported
Top Score
Info
Self Reported
Source
z.AI
GLM 5V Turbo
01 Apr 2026
75.70%
-
Yes
Source
Qwen
Qwen 3.8 27B
14 Aug 2026
81.90%
-
Yes
Source
Sign Up
Sign Up