Docs
Search
Ctrl K
Models
Chat
Compare
Providers
Apps
Rankings
Sign Up
Sign Up
PostTrain Bench Benchmark Leaderboard | Phaseo
PostTrain Bench
PostTrain Bench
AI benchmark results and model performance
Summary
▼
Summary
▼
Type: percentage
Agents
View benchmark source
Recorded Results
1
Average Score
36.60%
Scores Over Time
Individual benchmark scores plotted by date.
Models Using This Benchmark
Organisation
Model
Reported
Top Score
Info
Self Reported
Source
Moonshot
Kimi K3
16 Jul 2026
36.60%
Claude Code harness; official Harbor implementation at max reasoning effort; average of three runs.
Yes
Source
Score Range
36.60% - 36.60%
Leading Model (lowest score)
36.60% - Kimi K3