Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multilingual Language Understanding on MMMLU (ko, de, es, ja)
Loading...
88.9
Average Score
Qwen3.5-27B
76.836
79.968
83.1
86.232
Jan 5, 2026
Jan 20, 2026
Feb 5, 2026
Feb 21, 2026
Mar 8, 2026
Mar 24, 2026
Apr 9, 2026
Average Score
Updated 5d ago
Evaluation Results
Method
Method
Links
Average Score
Qwen3.5-27B
Architecture=Dense, #...
2026.04
88.9
GPT-5 mini
Reasoning Mode=REASONI...
2026.04
88.1
Qwen3-VL-235B-A22B
Architecture=MoE, # To...
2026.04
86.8
DeepSeek-V3.2
Mode=Non-Reasoning, Ar...
2026.01
86.3
K-EXAONE-236B-A23B
Architecture=MoE, # To...
2026.04
85.7
EXAONE 4.5 33B
Architecture=Dense, #...
2026.04
85.4
Qwen3-235B-A22B Instruct-2507
Architecture=MoE, Tota...
2026.01
84.5
K-EXAONE
Mode=Non-Reasoning, Ar...
2026.01
83.8
EXAONE 4.0
Mode=Non-Reasoning, Ar...
2026.01
77.3
Feedback
Search any
task
Search any
task