Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
STEM Knowledge on MMLU-Pro
Loading...
84.3
Accuracy
DeepSeek V3.2
81.388
82.144
82.9
83.656
Dec 30, 2025
Accuracy
Updated 5mo ago
Evaluation Results
Method
Method
Links
Accuracy
DeepSeek V3.2
Evaluation Mode=Chat
2025.12
84.3
LongCat-Flash Exp-Chat
Evaluation Mode=Chat
2025.12
84
LongCat-Flash Chat
Evaluation Mode=Chat
2025.12
82.7
GLM 4.6
Evaluation Mode=Chat
2025.12
81.5
Feedback
Search any
task
Search any
task
