Docs
Models
Chat
Compare
Providers
Apps
Rankings
Sign Up
Sign Up
Search
Ctrl K
BBEH Benchmark Leaderboard | Phaseo
BBEH
BBEH
AI benchmark results and model performance
Report an issue
Summary
▼
Summary
▼
Type: percentage
Reasoning
View benchmark source
Recorded Results
1
Average Score
27.20%
Scores Over Time
Individual benchmark scores plotted by date.
Model Results
Organisation
Model
Reported
Top Score
Info
Self Reported
Source
DeepSeek
DeepSeek V4.1 Flash
10 Sept 2026
27.20%
Base model; 1-shot; EM
Yes
Source
Score Range
27.20% - 27.20%
Leading Model (lowest score)
27.20% - DeepSeek V4.1 Flash
