Docs
Search
Ctrl K
Models
Chat
Compare
Providers
Apps
Rankings
Sign Up
Sign Up
MMLU Redux 2.0 Benchmark Leaderboard | Phaseo
MMLU Redux 2.0
MMLU Redux 2.0
AI benchmark results and model performance
Summary
▼
Summary
▼
Type: percentage
Recorded Results
1
Average Score
90.20%
Score Range
90.20% - 90.20%
Leading Model (lowest score)
90.20% - Kimi K2 (2025-07-11)
Scores Over Time
Individual benchmark scores plotted by date.
Models Using This Benchmark
Organisation
Model
Reported
Top Score
Info
Self Reported
Source
Moonshot
Kimi K2 (2025-07-11)
11 Jul 2025
90.20%
EM
Yes
Source